{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/7","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":177,"rows_per_page":100,"rows":[601,700],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling","prev":"/task/language-modelling/papers/6","next":"/task/language-modelling/papers/8","papers":[{"url":"/paper/seed-tts-a-family-of-high-quality-versatile","slug":"seed-tts-a-family-of-high-quality-versatile","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","date":"2024-06-04","arxiv_id":"2406.02430","repositories_listed":2,"syntology":null},{"url":"/paper/trutheval-a-dataset-to-evaluate-llm","slug":"trutheval-a-dataset-to-evaluate-llm","title":"TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability","date":"2024-06-04","arxiv_id":"2406.01855","repositories_listed":2,"syntology":null},{"url":"/paper/the-geometry-of-categorical-and-hierarchical","slug":"the-geometry-of-categorical-and-hierarchical","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","date":"2024-06-03","arxiv_id":"2406.01506","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/the-geometry-of-categorical-and-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2406.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01506"}},"official":{"repos":["kihopark/llm_categorical_hierarchical_representations"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llamea-a-large-language-model-evolutionary","slug":"llamea-a-large-language-model-evolutionary","title":"LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics","date":"2024-05-30","arxiv_id":"2405.20132","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llamea-a-large-language-model-evolutionary#ran","syntology_url":"https://syntology.ai/paper/2405.20132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20132"}},"official":{"repos":["nikivanstein/LLaMEA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cliploss-and-norm-based-data-selection","slug":"cliploss-and-norm-based-data-selection","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","date":"2024-05-29","arxiv_id":"2405.19547","repositories_listed":2,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":3,"n_no_contract":10,"n_pointer_only":19,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 3 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cliploss-and-norm-based-data-selection#ran","syntology_url":"https://syntology.ai/paper/2405.19547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19547"}},"official":{"repos":["ypwang61/negcliploss_normsim","ypwang61/VAS"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-circuits-in-pretrained-transformers","slug":"knowledge-circuits-in-pretrained-transformers","title":"Knowledge Circuits in Pretrained Transformers","date":"2024-05-28","arxiv_id":"2405.17969","repositories_listed":2,"syntology":null},{"url":"/paper/linguistic-collapse-neural-collapse-in-large","slug":"linguistic-collapse-neural-collapse-in-large","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","date":"2024-05-28","arxiv_id":"2405.17767","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linguistic-collapse-neural-collapse-in-large#ran","syntology_url":"https://syntology.ai/paper/2405.17767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17767"}},"official":{"repos":["rhubarbwu/linguistic-collapse","rhubarbwu/neural-collapse"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-experiments-with-simulation-large","slug":"llm-experiments-with-simulation-large","title":"LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins","date":"2024-05-28","arxiv_id":"2405.18092","repositories_listed":2,"syntology":null},{"url":"/paper/xformparser-a-simple-and-effective-multimodal","slug":"xformparser-a-simple-and-effective-multimodal","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","date":"2024-05-27","arxiv_id":"2405.17336","repositories_listed":2,"syntology":null},{"url":"/paper/cacheblend-fast-large-language-model-serving","slug":"cacheblend-fast-large-language-model-serving","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","date":"2024-05-26","arxiv_id":"2405.16444","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cacheblend-fast-large-language-model-serving#ran","syntology_url":"https://syntology.ai/paper/2405.16444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16444"}},"official":{"repos":["YaoJiayi/CacheBlend"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangling-and-integrating-relational-and","slug":"disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","arxiv_id":"2405.16727","repositories_listed":2,"syntology":{"n":21,"n_ran":14,"n_constructed":9,"n_ran_checked":10,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/disentangling-and-integrating-relational-and#ran","syntology_url":"https://syntology.ai/paper/2405.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16727"}},"official":{"repos":["awni00/dual-attention"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/detikzify-synthesizing-graphics-programs-for","slug":"detikzify-synthesizing-graphics-programs-for","title":"DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ","date":"2024-05-24","arxiv_id":"2405.15306","repositories_listed":2,"syntology":{"n":8,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/detikzify-synthesizing-graphics-programs-for#ran","syntology_url":"https://syntology.ai/paper/2405.15306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15306"}},"official":{"repos":["potamides/detikzify"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/detox-toxic-subspace-projection-for-model","slug":"detox-toxic-subspace-projection-for-model","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","date":"2024-05-22","arxiv_id":"2405.13967","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/detox-toxic-subspace-projection-for-model#ran","syntology_url":"https://syntology.ai/paper/2405.13967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13967"}},"official":{"repos":["uppaal/detox-edit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/hw-gpt-bench-hardware-aware-architecture","slug":"hw-gpt-bench-hardware-aware-architecture","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","date":"2024-05-16","arxiv_id":"2405.10299","repositories_listed":2,"syntology":null},{"url":"/paper/improving-transformers-with-dynamically","slug":"improving-transformers-with-dynamically","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","date":"2024-05-14","arxiv_id":"2405.08553","repositories_listed":2,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improving-transformers-with-dynamically#ran","syntology_url":"https://syntology.ai/paper/2405.08553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08553"}},"official":{"repos":["caiyun-ai/dcformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-systematic-investigation-of-distilling","slug":"a-systematic-investigation-of-distilling","title":"Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking","date":"2024-05-13","arxiv_id":"2405.07920","repositories_listed":2,"syntology":null},{"url":"/paper/diffmatch-visual-language-guidance-makes","slug":"diffmatch-visual-language-guidance-makes","title":"SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector","date":"2024-05-08","arxiv_id":"2405.04788","repositories_listed":2,"syntology":null},{"url":"/paper/swe-agent-agent-computer-interfaces-enable","slug":"swe-agent-agent-computer-interfaces-enable","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","date":"2024-05-06","arxiv_id":"2405.15793","repositories_listed":2,"syntology":null},{"url":"/paper/huixiangdou-cr-coreference-resolution-in","slug":"huixiangdou-cr-coreference-resolution-in","title":"Labeling supervised fine-tuning data with the scaling law","date":"2024-05-05","arxiv_id":"2405.02817","repositories_listed":2,"syntology":null},{"url":"/paper/causal-evaluation-of-language-models","slug":"causal-evaluation-of-language-models","title":"Causal Evaluation of Language Models","date":"2024-05-01","arxiv_id":"2405.00622","repositories_listed":2,"syntology":null},{"url":"/paper/rag-and-rau-a-survey-on-retrieval-augmented","slug":"rag-and-rau-a-survey-on-retrieval-augmented","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","date":"2024-04-30","arxiv_id":"2404.19543","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rag-and-rau-a-survey-on-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.19543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19543"}},"official":{"repos":["2471023025/ralm_survey"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/how-good-are-low-bit-quantized-llama3-models","slug":"how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","arxiv_id":"2404.14047","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-good-are-low-bit-quantized-llama3-models#ran","syntology_url":"https://syntology.ai/paper/2404.14047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14047"}},"official":{"repos":["macaronlin/llama3-quantization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/forcing-diffuse-distributions-out-of-language","slug":"forcing-diffuse-distributions-out-of-language","title":"Forcing Diffuse Distributions out of Language Models","date":"2024-04-16","arxiv_id":"2404.10859","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/forcing-diffuse-distributions-out-of-language#ran","syntology_url":"https://syntology.ai/paper/2404.10859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10859"}},"official":{"repos":["y0mingzhang/diffuse-distributions","y0mingzhang/diffuse-probabilities"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/photo-realistic-image-restoration-in-the-wild","slug":"photo-realistic-image-restoration-in-the-wild","title":"Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models","date":"2024-04-15","arxiv_id":"2404.09732","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/photo-realistic-image-restoration-in-the-wild#ran","syntology_url":"https://syntology.ai/paper/2404.09732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09732"}},"official":{"repos":["algolzw/daclip-uir"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ming-moe-enhancing-medical-multi-task","slug":"ming-moe-enhancing-medical-multi-task","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","date":"2024-04-13","arxiv_id":"2404.09027","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ming-moe-enhancing-medical-multi-task#ran","syntology_url":"https://syntology.ai/paper/2404.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09027"}},"official":{"repos":["mediabrain-sjtu/ming"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/internlm-xcomposer2-4khd-a-pioneering-large","slug":"internlm-xcomposer2-4khd-a-pioneering-large","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","date":"2024-04-09","arxiv_id":"2404.06512","repositories_listed":2,"syntology":null},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/nicolay-r-at-semeval-2024-task-3-using-flan","slug":"nicolay-r-at-semeval-2024-task-3-using-flan","title":"nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States","date":"2024-04-04","arxiv_id":"2404.03361","repositories_listed":2,"syntology":null},{"url":"/paper/codebenchgen-creating-scalable-execution","slug":"codebenchgen-creating-scalable-execution","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","date":"2024-03-31","arxiv_id":"2404.00566","repositories_listed":2,"syntology":null},{"url":"/paper/extensive-self-contrast-enables-feedback-free","slug":"extensive-self-contrast-enables-feedback-free","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment","date":"2024-03-31","arxiv_id":"2404.00604","repositories_listed":2,"syntology":null},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-gemma-accelerating-multimodal","slug":"llava-gemma-accelerating-multimodal","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model","date":"2024-03-29","arxiv_id":"2404.01331","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llava-gemma-accelerating-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.01331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01331"}},"official":{"repos":["intellabs/multimodal_cognitive_ai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-feature-circuits-discovering-and","slug":"sparse-feature-circuits-discovering-and","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","date":"2024-03-28","arxiv_id":"2403.19647","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sparse-feature-circuits-discovering-and#ran","syntology_url":"https://syntology.ai/paper/2403.19647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19647"}},"official":{"repos":["saprmarks/feature-circuits"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tablellm-enabling-tabular-data-manipulation","slug":"tablellm-enabling-tabular-data-manipulation","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","date":"2024-03-28","arxiv_id":"2403.19318","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tablellm-enabling-tabular-data-manipulation#ran","syntology_url":"https://syntology.ai/paper/2403.19318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19318"}},"official":{"repos":["TableLLM/TableLLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-your-language-a-multilingual-dataset-for","slug":"mind-your-language-a-multilingual-dataset-for","title":"MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendation","date":"2024-03-26","arxiv_id":"2403.17876","repositories_listed":2,"syntology":null},{"url":"/paper/llm-agent-operating-system","slug":"llm-agent-operating-system","title":"AIOS: LLM Agent Operating System","date":"2024-03-25","arxiv_id":"2403.16971","repositories_listed":2,"syntology":null},{"url":"/paper/lexicon-level-contrastive-visual-grounding","slug":"lexicon-level-contrastive-visual-grounding","title":"Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling","date":"2024-03-21","arxiv_id":"2403.14551","repositories_listed":2,"syntology":null},{"url":"/paper/regularized-adaptive-momentum-dual-averaging","slug":"regularized-adaptive-momentum-dual-averaging","title":"Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network","date":"2024-03-21","arxiv_id":"2403.14398","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":1,"n_ran_checked":4,"n_instrument":8,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":16,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/regularized-adaptive-momentum-dual-averaging#ran","syntology_url":"https://syntology.ai/paper/2403.14398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14398"}},"official":{"repos":["ismoptgroup/ramda","ismoptgroup/ramda_exp"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/rewardbench-evaluating-reward-models-for","slug":"rewardbench-evaluating-reward-models-for","title":"RewardBench: Evaluating Reward Models for Language Modeling","date":"2024-03-20","arxiv_id":"2403.13787","repositories_listed":2,"syntology":null},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sq-llava-self-questioning-for-large-vision","slug":"sq-llava-self-questioning-for-large-vision","title":"SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant","date":"2024-03-17","arxiv_id":"2403.11299","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sq-llava-self-questioning-for-large-vision#ran","syntology_url":"https://syntology.ai/paper/2403.11299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11299"}},"official":{"repos":["heliossun/sq-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/training-a-small-emotional-vision-language","slug":"training-a-small-emotional-vision-language","title":"Training A Small Emotional Vision Language Model for Visual Art Comprehension","date":"2024-03-17","arxiv_id":"2403.11150","repositories_listed":2,"syntology":null},{"url":"/paper/videoagent-long-form-video-understanding-with","slug":"videoagent-long-form-video-understanding-with","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","date":"2024-03-15","arxiv_id":"2403.10517","repositories_listed":2,"syntology":null},{"url":"/paper/quiet-star-language-models-can-teach","slug":"quiet-star-language-models-can-teach","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","date":"2024-03-14","arxiv_id":"2403.09629","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quiet-star-language-models-can-teach#ran","syntology_url":"https://syntology.ai/paper/2403.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09629"}},"official":{"repos":["ezelikman/quiet-star"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}},"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bridging-different-language-models-and","slug":"bridging-different-language-models-and","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","date":"2024-03-12","arxiv_id":"2403.07860","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-different-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2403.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07860"}},"official":{"repos":["shihaozhaozsh/lavi-bridge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decomposing-disease-descriptions-for-enhanced","slug":"decomposing-disease-descriptions-for-enhanced","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","date":"2024-03-12","arxiv_id":"2403.07636","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decomposing-disease-descriptions-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2403.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07636"}},"official":{"repos":["hieuphan33/mavl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/workarena-how-capable-are-web-agents-at","slug":"workarena-how-capable-are-web-agents-at","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","date":"2024-03-12","arxiv_id":"2403.07718","repositories_listed":2,"syntology":null},{"url":"/paper/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ella-equip-diffusion-models-with-llm-for#ran","syntology_url":"https://syntology.ai/paper/2403.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05135"}},"official":null}},{"url":"/paper/injecagent-benchmarking-indirect-prompt","slug":"injecagent-benchmarking-indirect-prompt","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","date":"2024-03-05","arxiv_id":"2403.02691","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/injecagent-benchmarking-indirect-prompt#ran","syntology_url":"https://syntology.ai/paper/2403.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02691"}},"official":{"repos":["uiuc-kang-lab/injecagent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-scale-protein-language-model-for","slug":"multi-scale-protein-language-model-for","title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","date":"2024-03-05","arxiv_id":"2403.12995","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-scale-protein-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2403.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12995"}},"official":{"repos":["zhengkangjie/esm-aa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","repositories_listed":2,"syntology":null},{"url":"/paper/wukong-towards-a-scaling-law-for-large-scale","slug":"wukong-towards-a-scaling-law-for-large-scale","title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","date":"2024-03-04","arxiv_id":"2403.02545","repositories_listed":2,"syntology":null},{"url":"/paper/intactkv-improving-large-language-model","slug":"intactkv-improving-large-language-model","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","date":"2024-03-02","arxiv_id":"2403.01241","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/intactkv-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01241"}},"official":{"repos":["ruikangliu/IntactKV"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/archer-training-language-model-agents-via","slug":"archer-training-language-model-agents-via","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","date":"2024-02-29","arxiv_id":"2402.19446","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/archer-training-language-model-agents-via#ran","syntology_url":"https://syntology.ai/paper/2402.19446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19446"}},"official":{"repos":["yifeizhou02/archer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rinalmo-general-purpose-rna-language-models","slug":"rinalmo-general-purpose-rna-language-models","title":"RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks","date":"2024-02-29","arxiv_id":"2403.00043","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rinalmo-general-purpose-rna-language-models#ran","syntology_url":"https://syntology.ai/paper/2403.00043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00043"}},"official":{"repos":["lbcb-sci/rinalmo","ml4bio/rna-fm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-generate-instruction-tuning","slug":"learning-to-generate-instruction-tuning","title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation","date":"2024-02-28","arxiv_id":"2402.18334","repositories_listed":2,"syntology":null},{"url":"/paper/defending-llms-against-jailbreaking-attacks","slug":"defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","arxiv_id":"2402.16459","repositories_listed":2,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/defending-llms-against-jailbreaking-attacks#ran","syntology_url":"https://syntology.ai/paper/2402.16459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16459"}},"official":{"repos":["yihanwang617/llm-jailbreaking-defense","yihanwang617/llm-jailbreaking-defense-backtranslation"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-inference-unveiled-survey-and-roofline","slug":"llm-inference-unveiled-survey-and-roofline","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","date":"2024-02-26","arxiv_id":"2402.16363","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-inference-unveiled-survey-and-roofline#ran","syntology_url":"https://syntology.ai/paper/2402.16363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16363"}},"official":{"repos":["hahnyuan/llm-viewer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lstp-language-guided-spatial-temporal-prompt","slug":"lstp-language-guided-spatial-temporal-prompt","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","date":"2024-02-25","arxiv_id":"2402.16050","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lstp-language-guided-spatial-temporal-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16050"}},"official":{"repos":["bigai-nlco/lstp-chat","bigai-nlco/videotgb"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mathwell-generating-educational-math-word","slug":"mathwell-generating-educational-math-word","title":"MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations","date":"2024-02-24","arxiv_id":"2402.15861","repositories_listed":2,"syntology":null},{"url":"/paper/self-retrieval-building-an-information","slug":"self-retrieval-building-an-information","title":"Self-Retrieval: End-to-End Information Retrieval with One Large Language Model","date":"2024-02-23","arxiv_id":"2403.00801","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-retrieval-building-an-information#ran","syntology_url":"https://syntology.ai/paper/2403.00801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00801"}},"official":{"repos":["icip-cas/selfretrieval","tangqiaoyu/selfretrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/criticbench-evaluating-large-language-models","slug":"criticbench-evaluating-large-language-models","title":"CriticEval: Evaluating Large Language Model as Critic","date":"2024-02-21","arxiv_id":"2402.13764","repositories_listed":2,"syntology":null},{"url":"/paper/softmax-probabilities-mostly-predict-large","slug":"softmax-probabilities-mostly-predict-large","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","date":"2024-02-20","arxiv_id":"2402.13213","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/softmax-probabilities-mostly-predict-large#ran","syntology_url":"https://syntology.ai/paper/2402.13213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13213"}},"official":{"repos":["bplaut/softmax-probs-predict-llm-correctness","bplaut/llm-calibration-and-correctness-prediction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/trap-targeted-random-adversarial-prompt","slug":"trap-targeted-random-adversarial-prompt","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","date":"2024-02-20","arxiv_id":"2402.12991","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trap-targeted-random-adversarial-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.12991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12991"}},"official":{"repos":["framartin/trap","parameterlab/trap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/generation-meets-verification-accelerating","slug":"generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","arxiv_id":"2402.11809","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generation-meets-verification-accelerating#ran","syntology_url":"https://syntology.ai/paper/2402.11809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11809"}},"official":{"repos":["cteant/space","hiyouga/llama-factory"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/query-based-adversarial-prompt-generation","slug":"query-based-adversarial-prompt-generation","title":"Query-Based Adversarial Prompt Generation","date":"2024-02-19","arxiv_id":"2402.12329","repositories_listed":2,"syntology":null},{"url":"/paper/laco-large-language-model-pruning-via-layer","slug":"laco-large-language-model-pruning-via-layer","title":"LaCo: Large Language Model Pruning via Layer Collapse","date":"2024-02-17","arxiv_id":"2402.11187","repositories_listed":2,"syntology":null},{"url":"/paper/direct-preference-optimization-with-an-offset","slug":"direct-preference-optimization-with-an-offset","title":"Direct Preference Optimization with an Offset","date":"2024-02-16","arxiv_id":"2402.10571","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/direct-preference-optimization-with-an-offset#ran","syntology_url":"https://syntology.ai/paper/2402.10571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10571"}},"official":{"repos":["rycolab/odpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/linear-transformers-with-learnable-kernel","slug":"linear-transformers-with-learnable-kernel","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","date":"2024-02-16","arxiv_id":"2402.10644","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/linear-transformers-with-learnable-kernel#ran","syntology_url":"https://syntology.ai/paper/2402.10644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10644"}},"official":{"repos":["sustcsonglin/flash-linear-attention","corl-team/rebased"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/de-cop-detecting-copyrighted-content-in","slug":"de-cop-detecting-copyrighted-content-in","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","date":"2024-02-15","arxiv_id":"2402.09910","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/de-cop-detecting-copyrighted-content-in#ran","syntology_url":"https://syntology.ai/paper/2402.09910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09910"}},"official":{"repos":["avduarte333/de-cop_method","leililab/de-cop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-representational-instruction","slug":"generative-representational-instruction","title":"Generative Representational Instruction Tuning","date":"2024-02-15","arxiv_id":"2402.09906","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-representational-instruction#ran","syntology_url":"https://syntology.ai/paper/2402.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09906"}},"official":{"repos":["contextualai/gritlm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-segmentation-with-unpaired","slug":"open-vocabulary-segmentation-with-unpaired","title":"Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision","date":"2024-02-14","arxiv_id":"2402.08960","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/open-vocabulary-segmentation-with-unpaired#ran","syntology_url":"https://syntology.ai/paper/2402.08960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08960"}},"official":{"repos":["derrickwang005/uni-ovseg.pytorch","derrickwang005/unpair-seg.pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automathtext-autonomous-data-selection-with","slug":"automathtext-autonomous-data-selection-with","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","date":"2024-02-12","arxiv_id":"2402.07625","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automathtext-autonomous-data-selection-with#ran","syntology_url":"https://syntology.ai/paper/2402.07625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07625"}},"official":{"repos":["hiyouga/llama-factory","yifanzhang-pro/automathtext"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/realm-rag-driven-enhancement-of-multimodal","slug":"realm-rag-driven-enhancement-of-multimodal","title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models","date":"2024-02-10","arxiv_id":"2402.07016","repositories_listed":2,"syntology":null},{"url":"/paper/screenai-a-vision-language-model-for-ui-and","slug":"screenai-a-vision-language-model-for-ui-and","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","date":"2024-02-07","arxiv_id":"2402.04615","repositories_listed":2,"syntology":null},{"url":"/paper/can-mamba-learn-how-to-learn-a-comparative","slug":"can-mamba-learn-how-to-learn-a-comparative","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","date":"2024-02-06","arxiv_id":"2402.04248","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-mamba-learn-how-to-learn-a-comparative#ran","syntology_url":"https://syntology.ai/paper/2402.04248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04248"}},"official":{"repos":["krafton-ai/mambaformer-icl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-implicit-bias-in-explicitly","slug":"measuring-implicit-bias-in-explicitly","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","date":"2024-02-06","arxiv_id":"2402.04105","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-implicit-bias-in-explicitly#ran","syntology_url":"https://syntology.ai/paper/2402.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04105"}},"official":{"repos":["baixuechunzi/llm-implicit-bias"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/jailbreaking-attack-against-multimodal-large","slug":"jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","arxiv_id":"2402.02309","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jailbreaking-attack-against-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02309"}},"official":{"repos":["abc03570128/jailbreaking-attack-against-multimodal-large-language-model"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/variance-alignment-score-a-simple-but-tough","slug":"variance-alignment-score-a-simple-but-tough","title":"Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning","date":"2024-02-03","arxiv_id":"2402.02055","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/variance-alignment-score-a-simple-but-tough#ran","syntology_url":"https://syntology.ai/paper/2402.02055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02055"}},"official":null}},{"url":"/paper/integrating-large-language-models-in-causal","slug":"integrating-large-language-models-in-causal","title":"Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach","date":"2024-02-02","arxiv_id":"2402.01454","repositories_listed":2,"syntology":null},{"url":"/paper/executable-code-actions-elicit-better-llm","slug":"executable-code-actions-elicit-better-llm","title":"Executable Code Actions Elicit Better LLM Agents","date":"2024-02-01","arxiv_id":"2402.01030","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/executable-code-actions-elicit-better-llm#ran","syntology_url":"https://syntology.ai/paper/2402.01030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01030"}},"official":{"repos":["epfllm/megatron-llm","xingyaoww/code-act"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/towards-efficient-and-exact-optimization-of","slug":"towards-efficient-and-exact-optimization-of","title":"Towards Efficient Exact Optimization of Language Model Alignment","date":"2024-02-01","arxiv_id":"2402.00856","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-efficient-and-exact-optimization-of#ran","syntology_url":"https://syntology.ai/paper/2402.00856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00856"}},"official":{"repos":["haozheji/exact-optimization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lanegraph2seq-lane-topology-extraction-with","slug":"lanegraph2seq-lane-topology-extraction-with","title":"LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement","date":"2024-01-31","arxiv_id":"2401.17609","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lanegraph2seq-lane-topology-extraction-with#ran","syntology_url":"https://syntology.ai/paper/2401.17609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17609"}},"official":{"repos":["fudan-zvg/roadnet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/arrows-of-time-for-large-language-models","slug":"arrows-of-time-for-large-language-models","title":"Arrows of Time for Large Language Models","date":"2024-01-30","arxiv_id":"2401.17505","repositories_listed":2,"syntology":null},{"url":"/paper/infini-gram-scaling-unbounded-n-gram-language","slug":"infini-gram-scaling-unbounded-n-gram-language","title":"Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens","date":"2024-01-30","arxiv_id":"2401.17377","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infini-gram-scaling-unbounded-n-gram-language#ran","syntology_url":"https://syntology.ai/paper/2401.17377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17377"}},"official":{"repos":["liujch1998/infini-gram"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-evaluation-via-matrix","slug":"large-language-model-evaluation-via-matrix","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","date":"2024-01-30","arxiv_id":"2401.17139","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-evaluation-via-matrix#ran","syntology_url":"https://syntology.ai/paper/2401.17139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17139"}},"official":{"repos":["waltonfuture/Diff-eRank"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/l-autoda-leveraging-large-language-models-for","slug":"l-autoda-leveraging-large-language-models-for","title":"L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks","date":"2024-01-27","arxiv_id":"2401.15335","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l-autoda-leveraging-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.15335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15335"}},"official":{"repos":["pgg3/L-AutoDA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/turna-a-turkish-encoder-decoder-language","slug":"turna-a-turkish-encoder-decoder-language","title":"TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation","date":"2024-01-25","arxiv_id":"2401.14373","repositories_listed":2,"syntology":null},{"url":"/paper/tool-lmm-a-large-multi-modal-model-for-tool","slug":"tool-lmm-a-large-multi-modal-model-for-tool","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","date":"2024-01-19","arxiv_id":"2401.10727","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tool-lmm-a-large-multi-modal-model-for-tool#ran","syntology_url":"https://syntology.ai/paper/2401.10727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10727"}},"official":{"repos":["mllm-tool/mllm-tool","tool-lmm/tool-lmm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vlogger-make-your-dream-a-vlog","slug":"vlogger-make-your-dream-a-vlog","title":"Vlogger: Make Your Dream A Vlog","date":"2024-01-17","arxiv_id":"2401.09414","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vlogger-make-your-dream-a-vlog#ran","syntology_url":"https://syntology.ai/paper/2401.09414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09414"}},"official":{"repos":["zhuangshaobin/vlogger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-efficiency-in-large-language-model","slug":"unlocking-efficiency-in-large-language-model","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","date":"2024-01-15","arxiv_id":"2401.07851","repositories_listed":2,"syntology":null},{"url":"/paper/deepseekmoe-towards-ultimate-expert","slug":"deepseekmoe-towards-ultimate-expert","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","date":"2024-01-11","arxiv_id":"2401.06066","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseekmoe-towards-ultimate-expert#ran","syntology_url":"https://syntology.ai/paper/2401.06066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06066"}},"official":{"repos":["deepseek-ai/deepseek-moe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lego-language-enhanced-multi-modal-grounding","slug":"lego-language-enhanced-multi-modal-grounding","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","date":"2024-01-11","arxiv_id":"2401.06071","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lego-language-enhanced-multi-modal-grounding#ran","syntology_url":"https://syntology.ai/paper/2401.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06071"}},"official":{"repos":["lzw-lzw/groundinggpt","lzw-lzw/lego"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-model-agency-through","slug":"evaluating-language-model-agency-through","title":"Evaluating Language Model Agency through Negotiations","date":"2024-01-09","arxiv_id":"2401.04536","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-language-model-agency-through#ran","syntology_url":"https://syntology.ai/paper/2401.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04536"}},"official":{"repos":["epfl-dlab/lamen"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comparative-analysis-of-llama-and-chatgpt","slug":"comparative-analysis-of-llama-and-chatgpt","title":"Can Large Language Models Understand Molecules?","date":"2024-01-05","arxiv_id":"2402.00024","repositories_listed":2,"syntology":null},{"url":"/paper/tinyllama-an-open-source-small-language-model","slug":"tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","arxiv_id":"2401.02385","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tinyllama-an-open-source-small-language-model#ran","syntology_url":"https://syntology.ai/paper/2401.02385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02385"}},"official":{"repos":["Lightning-AI/lit-gpt","jzhang38/tinyllama"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-mechanistic-understanding-of-alignment","slug":"a-mechanistic-understanding-of-alignment","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","date":"2024-01-03","arxiv_id":"2401.01967","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-mechanistic-understanding-of-alignment#ran","syntology_url":"https://syntology.ai/paper/2401.01967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01967"}},"official":{"repos":["ajyl/dpo_toxic"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"3d52c632002ef2ee053845902c27bdfd03048595e4bf9dc98961959922ff573d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}