{"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-modeling/papers/22","list_of":"/task/language-modeling","task":"Language Modeling","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":22,"pages_in_order":142,"rows_per_page":100,"rows":[2101,2200],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling","prev":"/task/language-modeling/papers/21","next":"/task/language-modeling/papers/23","papers":[{"url":"/paper/how-transformers-learn-structured-data","slug":"how-transformers-learn-structured-data","title":"How transformers learn structured data: insights from hierarchical filtering","date":"2024-08-27","arxiv_id":"2408.15138","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/how-transformers-learn-structured-data#ran","syntology_url":"https://syntology.ai/paper/2408.15138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15138"}},"official":{"repos":["emanuele-moscato/tree-language-paper-submission"],"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/llm-defenses-are-not-robust-to-multi-turn","slug":"llm-defenses-are-not-robust-to-multi-turn","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","date":"2024-08-27","arxiv_id":"2408.15221","repositories_listed":1,"syntology":null},{"url":"/paper/project-shadow-symbolic-higher-order","slug":"project-shadow-symbolic-higher-order","title":"Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing","date":"2024-08-27","arxiv_id":"2408.14849","repositories_listed":1,"syntology":null},{"url":"/paper/rsteller-scaling-up-visual-language-modeling","slug":"rsteller-scaling-up-visual-language-modeling","title":"RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models","date":"2024-08-27","arxiv_id":"2408.14744","repositories_listed":1,"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/rsteller-scaling-up-visual-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2408.14744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14744"}},"official":{"repos":["slytheringe/rsteller"],"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/spikingssms-learning-long-sequences-with","slug":"spikingssms-learning-long-sequences-with","title":"SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models","date":"2024-08-27","arxiv_id":"2408.14909","repositories_listed":1,"syntology":null},{"url":"/paper/xg-nid-dual-modality-network-intrusion","slug":"xg-nid-dual-modality-network-intrusion","title":"XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model","date":"2024-08-27","arxiv_id":"2408.16021","repositories_listed":1,"syntology":null},{"url":"/paper/agentmove-predicting-human-mobility-anywhere","slug":"agentmove-predicting-human-mobility-anywhere","title":"AgentMove: Predicting Human Mobility Anywhere Using Large Language Model based Agentic Framework","date":"2024-08-26","arxiv_id":"2408.13986","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agentmove-predicting-human-mobility-anywhere#ran","syntology_url":"https://syntology.ai/paper/2408.13986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13986"}},"official":{"repos":["tsinghua-fib-lab/agentmove"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-evaluation-of-explanation-methods-for","slug":"an-evaluation-of-explanation-methods-for","title":"An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Text","date":"2024-08-26","arxiv_id":"2408.14252","repositories_listed":1,"syntology":null},{"url":"/paper/chartom-a-visual-theory-of-mind-benchmark-for","slug":"chartom-a-visual-theory-of-mind-benchmark-for","title":"CHARTOM: A Visual Theory-of-Mind Benchmark for Multimodal Large Language Models","date":"2024-08-26","arxiv_id":"2408.14419","repositories_listed":1,"syntology":null},{"url":"/paper/mlr-copilot-autonomous-machine-learning","slug":"mlr-copilot-autonomous-machine-learning","title":"MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents","date":"2024-08-26","arxiv_id":"2408.14033","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"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) · 7 unverified","sample_list":"/paper/mlr-copilot-autonomous-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2408.14033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14033"}},"official":{"repos":["du-nlp-lab/mlr-copilot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/question-answering-system-of-bridge-design","slug":"question-answering-system-of-bridge-design","title":"Question answering system of bridge design specification based on large language model","date":"2024-08-26","arxiv_id":"2408.13282","repositories_listed":1,"syntology":null},{"url":"/paper/social-perception-of-faces-in-a-vision","slug":"social-perception-of-faces-in-a-vision","title":"Social perception of faces in a vision-language model","date":"2024-08-26","arxiv_id":"2408.14435","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/social-perception-of-faces-in-a-vision#ran","syntology_url":"https://syntology.ai/paper/2408.14435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14435"}},"official":{"repos":["carinahausladen/clip-face-bias"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","repositories_listed":1,"syntology":null},{"url":"/paper/llamaduo-llmops-pipeline-for-seamless","slug":"llamaduo-llmops-pipeline-for-seamless","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","date":"2024-08-24","arxiv_id":"2408.13467","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/llamaduo-llmops-pipeline-for-seamless#ran","syntology_url":"https://syntology.ai/paper/2408.13467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13467"}},"official":{"repos":["deep-diver/llamaduo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/iaa-inner-adaptor-architecture-empowers","slug":"iaa-inner-adaptor-architecture-empowers","title":"IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities","date":"2024-08-23","arxiv_id":"2408.12902","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/iaa-inner-adaptor-architecture-empowers#ran","syntology_url":"https://syntology.ai/paper/2408.12902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12902"}},"official":{"repos":["360cvgroup/inner-adaptor-architecture"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/limp-large-language-model-enhanced-intent","slug":"limp-large-language-model-enhanced-intent","title":"LIMP: Large Language Model Enhanced Intent-aware Mobility Prediction","date":"2024-08-23","arxiv_id":"2408.12832","repositories_listed":1,"syntology":null},{"url":"/paper/evidence-backed-fact-checking-using-rag-and","slug":"evidence-backed-fact-checking-using-rag-and","title":"Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs","date":"2024-08-22","arxiv_id":"2408.12060","repositories_listed":1,"syntology":null},{"url":"/paper/fidavl-fake-image-detection-and-attribution","slug":"fidavl-fake-image-detection-and-attribution","title":"FIDAVL: Fake Image Detection and Attribution using Vision-Language Model","date":"2024-08-22","arxiv_id":"2409.03109","repositories_listed":1,"syntology":null},{"url":"/paper/first-teach-a-reliable-large-language-model","slug":"first-teach-a-reliable-large-language-model","title":"FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation","date":"2024-08-22","arxiv_id":"2408.12168","repositories_listed":1,"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/first-teach-a-reliable-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.12168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12168"}},"official":{"repos":["shumkashun/first"],"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/slm-meets-llm-balancing-latency","slug":"slm-meets-llm-balancing-latency","title":"SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection","date":"2024-08-22","arxiv_id":"2408.12748","repositories_listed":1,"syntology":null},{"url":"/paper/approaching-deep-learning-through-the","slug":"approaching-deep-learning-through-the","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","date":"2024-08-21","arxiv_id":"2408.11804","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/approaching-deep-learning-through-the#ran","syntology_url":"https://syntology.ai/paper/2408.11804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11804"}},"official":{"repos":["dyunis/spectral_dynamics"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/focusllm-scaling-llm-s-context-by-parallel","slug":"focusllm-scaling-llm-s-context-by-parallel","title":"FocusLLM: Precise Understanding of Long Context by Dynamic Condensing","date":"2024-08-21","arxiv_id":"2408.11745","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"12 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/focusllm-scaling-llm-s-context-by-parallel#ran","syntology_url":"https://syntology.ai/paper/2408.11745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11745"}},"official":{"repos":["leezythu/focusllm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/great-memory-shallow-reasoning-limits-of-k-nn","slug":"great-memory-shallow-reasoning-limits-of-k-nn","title":"Great Memory, Shallow Reasoning: Limits of $k$NN-LMs","date":"2024-08-21","arxiv_id":"2408.11815","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/great-memory-shallow-reasoning-limits-of-k-nn#ran","syntology_url":"https://syntology.ai/paper/2408.11815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11815"}},"official":{"repos":["gsyfate/knnlm-limits"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/proteingpt-multimodal-llm-for-protein","slug":"proteingpt-multimodal-llm-for-protein","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","date":"2024-08-21","arxiv_id":"2408.11363","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/proteingpt-multimodal-llm-for-protein#ran","syntology_url":"https://syntology.ai/paper/2408.11363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11363"}},"official":{"repos":["proteingpt/proteingpt"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unifashion-a-unified-vision-language-model","slug":"unifashion-a-unified-vision-language-model","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","date":"2024-08-21","arxiv_id":"2408.11305","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifashion-a-unified-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11305"}},"official":{"repos":["xiangyu-mm/unifashion"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-dialogue-a-profile-dialogue-alignment","slug":"beyond-dialogue-a-profile-dialogue-alignment","title":"BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model","date":"2024-08-20","arxiv_id":"2408.10903","repositories_listed":1,"syntology":null},{"url":"/paper/colbert-retrieval-and-ensemble-response","slug":"colbert-retrieval-and-ensemble-response","title":"ColBERT Retrieval and Ensemble Response Scoring for Language Model Question Answering","date":"2024-08-20","arxiv_id":"2408.10808","repositories_listed":1,"syntology":null},{"url":"/paper/language-modeling-on-tabular-data-a-survey-of","slug":"language-modeling-on-tabular-data-a-survey-of","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","date":"2024-08-20","arxiv_id":"2408.10548","repositories_listed":1,"syntology":null},{"url":"/paper/mistral-splade-llms-for-for-better-learned","slug":"mistral-splade-llms-for-for-better-learned","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","date":"2024-08-20","arxiv_id":"2408.11119","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-guided-image-adaptive-neural-implicit","slug":"prompt-guided-image-adaptive-neural-implicit","title":"Prompt-Guided Image-Adaptive Neural Implicit Lookup Tables for Interpretable Image Enhancement","date":"2024-08-20","arxiv_id":"2408.11055","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-large-language-model-and","slug":"a-comparison-of-large-language-model-and","title":"A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks","date":"2024-08-19","arxiv_id":"2408.09656","repositories_listed":1,"syntology":null},{"url":"/paper/attribution-analysis-meets-model-editing","slug":"attribution-analysis-meets-model-editing","title":"Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit","date":"2024-08-19","arxiv_id":"2408.09916","repositories_listed":1,"syntology":null},{"url":"/paper/automl-guided-fusion-of-entity-and-llm-based","slug":"automl-guided-fusion-of-entity-and-llm-based","title":"AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification","date":"2024-08-19","arxiv_id":"2408.09794","repositories_listed":1,"syntology":null},{"url":"/paper/blade-benchmarking-language-model-agents-for","slug":"blade-benchmarking-language-model-agents-for","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","date":"2024-08-19","arxiv_id":"2408.09667","repositories_listed":1,"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/blade-benchmarking-language-model-agents-for#ran","syntology_url":"https://syntology.ai/paper/2408.09667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09667"}},"official":{"repos":["behavioral-data/blade"],"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/cmoraleval-a-moral-evaluation-benchmark-for","slug":"cmoraleval-a-moral-evaluation-benchmark-for","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","date":"2024-08-19","arxiv_id":"2408.09819","repositories_listed":1,"syntology":null},{"url":"/paper/ffaa-multimodal-large-language-model-based","slug":"ffaa-multimodal-large-language-model-based","title":"FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant","date":"2024-08-19","arxiv_id":"2408.10072","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ffaa-multimodal-large-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2408.10072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10072"}},"official":{"repos":["thu-huangzc/FFAA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/idea-enhancing-the-rule-learning-ability-of","slug":"idea-enhancing-the-rule-learning-ability-of","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","date":"2024-08-19","arxiv_id":"2408.10455","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/idea-enhancing-the-rule-learning-ability-of#ran","syntology_url":"https://syntology.ai/paper/2408.10455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10455"}},"official":{"repos":["kaiyuhe998/rulearn_idea"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/r2gencsr-retrieving-context-samples-for-large","slug":"r2gencsr-retrieving-context-samples-for-large","title":"R2GenCSR: Retrieving Context Samples for Large Language Model based X-ray Medical Report Generation","date":"2024-08-19","arxiv_id":"2408.09743","repositories_listed":1,"syntology":null},{"url":"/paper/transformers-to-ssms-distilling-quadratic","slug":"transformers-to-ssms-distilling-quadratic","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","date":"2024-08-19","arxiv_id":"2408.10189","repositories_listed":1,"syntology":null},{"url":"/paper/hiagent-hierarchical-working-memory","slug":"hiagent-hierarchical-working-memory","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","date":"2024-08-18","arxiv_id":"2408.09559","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"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: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hiagent-hierarchical-working-memory#ran","syntology_url":"https://syntology.ai/paper/2408.09559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09559"}},"official":{"repos":["hiagent2024/hiagent"],"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/generating-data-with-text-to-speech-and-large","slug":"generating-data-with-text-to-speech-and-large","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","date":"2024-08-17","arxiv_id":"2408.09215","repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-model-for-photo-sharing-multi","slug":"an-end-to-end-model-for-photo-sharing-multi","title":"An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation","date":"2024-08-16","arxiv_id":"2408.08650","repositories_listed":1,"syntology":null},{"url":"/paper/ecg-chat-a-large-ecg-language-model-for","slug":"ecg-chat-a-large-ecg-language-model-for","title":"ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis","date":"2024-08-16","arxiv_id":"2408.08849","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"6 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; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ecg-chat-a-large-ecg-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2408.08849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08849"}},"official":{"repos":["YubaoZhao/ECG-Chat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/mrna2vec-mrna-embedding-with-language-model","slug":"mrna2vec-mrna-embedding-with-language-model","title":"mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design","date":"2024-08-16","arxiv_id":"2408.09048","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-validity-of-word-level","slug":"evaluating-the-validity-of-word-level","title":"Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models","date":"2024-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-web-crawled-data-for-high-quality","slug":"leveraging-web-crawled-data-for-high-quality","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","date":"2024-08-15","arxiv_id":"2408.08003","repositories_listed":1,"syntology":null},{"url":"/paper/text2bim-generating-building-models-using-a","slug":"text2bim-generating-building-models-using-a","title":"Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework","date":"2024-08-15","arxiv_id":"2408.08054","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/text2bim-generating-building-models-using-a#ran","syntology_url":"https://syntology.ai/paper/2408.08054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08054"}},"official":{"repos":["dcy0577/Text2BIM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/datavist5-a-pre-trained-language-model-for","slug":"datavist5-a-pre-trained-language-model-for","title":"DataVisT5: A Pre-trained Language Model for Jointly Understanding Text and Data Visualization","date":"2024-08-14","arxiv_id":"2408.07401","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-and-understanding-bridging-vision-with","slug":"seeing-and-understanding-bridging-vision-with","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","date":"2024-08-14","arxiv_id":"2408.07246","repositories_listed":1,"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":5,"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/seeing-and-understanding-bridging-vision-with#ran","syntology_url":"https://syntology.ai/paper/2408.07246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07246"}},"official":{"repos":["AI4Chem/ChemVlm"],"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/causal-agent-based-on-large-language-model","slug":"causal-agent-based-on-large-language-model","title":"Causal Agent based on Large Language Model","date":"2024-08-13","arxiv_id":"2408.06849","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/causal-agent-based-on-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.06849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06849"}},"official":{"repos":["kairong-han/causal_agent"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-cultural-adaptability-of-a-large","slug":"evaluating-cultural-adaptability-of-a-large","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","date":"2024-08-13","arxiv_id":"2408.06929","repositories_listed":1,"syntology":null},{"url":"/paper/ifship-a-large-vision-language-model-for","slug":"ifship-a-large-vision-language-model-for","title":"IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models","date":"2024-08-13","arxiv_id":"2408.06631","repositories_listed":1,"syntology":null},{"url":"/paper/neural-embedding-of-beliefs-reveals-the-role","slug":"neural-embedding-of-beliefs-reveals-the-role","title":"A semantic embedding space based on large language models for modelling human beliefs","date":"2024-08-13","arxiv_id":"2408.07237","repositories_listed":1,"syntology":null},{"url":"/paper/the-advantages-of-context-specific-language","slug":"the-advantages-of-context-specific-language","title":"The advantages of context specific language models: the case of the Erasmian Language Model","date":"2024-08-13","arxiv_id":"2408.06931","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-efficiency-adaptive-masking-for","slug":"unlocking-efficiency-adaptive-masking-for","title":"Unlocking Efficiency: Adaptive Masking for Gene Transformer Models","date":"2024-08-13","arxiv_id":"2408.07180","repositories_listed":1,"syntology":null},{"url":"/paper/fuxitranyu-a-multilingual-large-language","slug":"fuxitranyu-a-multilingual-large-language","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","date":"2024-08-12","arxiv_id":"2408.06273","repositories_listed":1,"syntology":null},{"url":"/paper/on-effects-of-steering-latent-representation","slug":"on-effects-of-steering-latent-representation","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","date":"2024-08-12","arxiv_id":"2408.06223","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/on-effects-of-steering-latent-representation#ran","syntology_url":"https://syntology.ai/paper/2408.06223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06223"}},"official":{"repos":["RebelsNLU-jaist/llm-unlearning"],"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":["official"]}}},{"url":"/paper/prompto-an-open-source-library-for","slug":"prompto-an-open-source-library-for","title":"Prompto: An open source library for asynchronous querying of LLM endpoints","date":"2024-08-12","arxiv_id":"2408.11847","repositories_listed":1,"syntology":null},{"url":"/paper/towards-autonomous-agents-adaptive-planning","slug":"towards-autonomous-agents-adaptive-planning","title":"Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models","date":"2024-08-12","arxiv_id":"2408.06458","repositories_listed":1,"syntology":null},{"url":"/paper/xcompress-llm-assisted-python-based-text","slug":"xcompress-llm-assisted-python-based-text","title":"XCompress: LLM assisted Python-based text compression toolkit","date":"2024-08-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/li-tta-language-informed-test-time-adaptation","slug":"li-tta-language-informed-test-time-adaptation","title":"LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition","date":"2024-08-11","arxiv_id":"2408.05769","repositories_listed":1,"syntology":null},{"url":"/paper/vic-virtual-compiler-is-all-you-need-for","slug":"vic-virtual-compiler-is-all-you-need-for","title":"ViC: Virtual Compiler Is All You Need For Assembly Code Search","date":"2024-08-10","arxiv_id":"2408.06385","repositories_listed":1,"syntology":null},{"url":"/paper/avoid-wasted-annotation-costs-in-open-set","slug":"avoid-wasted-annotation-costs-in-open-set","title":"Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Model","date":"2024-08-09","arxiv_id":"2408.04917","repositories_listed":1,"syntology":null},{"url":"/paper/llava-vsd-large-language-and-vision-assistant","slug":"llava-vsd-large-language-and-vision-assistant","title":"LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description","date":"2024-08-09","arxiv_id":"2408.04957","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-owl3-towards-long-image-sequence","slug":"mplug-owl3-towards-long-image-sequence","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","date":"2024-08-09","arxiv_id":"2408.04840","repositories_listed":1,"syntology":null},{"url":"/paper/tasl-task-skill-localization-and","slug":"tasl-task-skill-localization-and","title":"KIF: Knowledge Identification and Fusion for Language Model Continual Learning","date":"2024-08-09","arxiv_id":"2408.05200","repositories_listed":1,"syntology":null},{"url":"/paper/unibench-visual-reasoning-requires-rethinking","slug":"unibench-visual-reasoning-requires-rethinking","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","date":"2024-08-09","arxiv_id":"2408.04810","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 4 unverified","sample_list":"/paper/unibench-visual-reasoning-requires-rethinking#ran","syntology_url":"https://syntology.ai/paper/2408.04810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04810"}},"official":{"repos":["facebookresearch/unibench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/unleashing-artificial-cognition-integrating","slug":"unleashing-artificial-cognition-integrating","title":"Unleashing Artificial Cognition: Integrating Multiple AI Systems","date":"2024-08-09","arxiv_id":"2408.04910","repositories_listed":1,"syntology":null},{"url":"/paper/vita-towards-open-source-interactive-omni","slug":"vita-towards-open-source-interactive-omni","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","date":"2024-08-09","arxiv_id":"2408.05211","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-guided-language-modeling","slug":"diffusion-guided-language-modeling","title":"Diffusion Guided Language Modeling","date":"2024-08-08","arxiv_id":"2408.04220","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-guided-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2408.04220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04220"}},"official":{"repos":["justinlovelace/diffusion-guided-lm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-model-math-reasoning-via","slug":"evaluating-language-model-math-reasoning-via","title":"Mathfish: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula","date":"2024-08-08","arxiv_id":"2408.04226","repositories_listed":1,"syntology":null},{"url":"/paper/medical-graph-rag-towards-safe-medical-large","slug":"medical-graph-rag-towards-safe-medical-large","title":"Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation","date":"2024-08-08","arxiv_id":"2408.04187","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/medical-graph-rag-towards-safe-medical-large#ran","syntology_url":"https://syntology.ai/paper/2408.04187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04187"}},"official":{"repos":["medicinetoken/medical-graph-rag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/open-domain-implicit-format-control-for-large","slug":"open-domain-implicit-format-control-for-large","title":"Open-domain Implicit Format Control for Large Language Model Generation","date":"2024-08-08","arxiv_id":"2408.04392","repositories_listed":1,"syntology":null},{"url":"/paper/semantics-or-spelling-probing-contextual-word","slug":"semantics-or-spelling-probing-contextual-word","title":"Semantics or spelling? Probing contextual word embeddings with orthographic noise","date":"2024-08-08","arxiv_id":"2408.04162","repositories_listed":1,"syntology":null},{"url":"/paper/trans-tokenization-and-cross-lingual","slug":"trans-tokenization-and-cross-lingual","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","date":"2024-08-08","arxiv_id":"2408.04303","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/trans-tokenization-and-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2408.04303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04303"}},"official":{"repos":["lagom-nlp/transtokenizer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/1-5-pints-technical-report-pretraining-in","slug":"1-5-pints-technical-report-pretraining-in","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","date":"2024-08-07","arxiv_id":"2408.03506","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/1-5-pints-technical-report-pretraining-in#ran","syntology_url":"https://syntology.ai/paper/2408.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03506"}},"official":{"repos":["Pints-AI/1.5-Pints"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/acl-ready-rag-based-assistant-for-the-acl","slug":"acl-ready-rag-based-assistant-for-the-acl","title":"ACL Ready: RAG Based Assistant for the ACL Checklist","date":"2024-08-07","arxiv_id":"2408.04675","repositories_listed":1,"syntology":null},{"url":"/paper/artvlm-attribute-recognition-through-vision","slug":"artvlm-attribute-recognition-through-vision","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","date":"2024-08-07","arxiv_id":"2408.04102","repositories_listed":1,"syntology":null},{"url":"/paper/egybert-a-large-language-model-pretrained-on","slug":"egybert-a-large-language-model-pretrained-on","title":"EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora","date":"2024-08-07","arxiv_id":"2408.03524","repositories_listed":1,"syntology":null},{"url":"/paper/handwritten-code-recognition-for-pen-and","slug":"handwritten-code-recognition-for-pen-and","title":"Handwritten Code Recognition for Pen-and-Paper CS Education","date":"2024-08-07","arxiv_id":"2408.07220","repositories_listed":1,"syntology":null},{"url":"/paper/is-child-directed-speech-effective-training","slug":"is-child-directed-speech-effective-training","title":"Is Child-Directed Speech Effective Training Data for Language Models?","date":"2024-08-07","arxiv_id":"2408.03617","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/is-child-directed-speech-effective-training#ran","syntology_url":"https://syntology.ai/paper/2408.03617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03617"}},"official":{"repos":["styfeng/tinydialogues"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03127","slug":"2408-03127","title":"Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation","date":"2024-08-06","arxiv_id":"2408.03127","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03149","slug":"2408-03149","title":"Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization","date":"2024-08-06","arxiv_id":"2408.03149","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03281","slug":"2408-03281","title":"StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation","date":"2024-08-06","arxiv_id":"2408.03281","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/2408-03281#ran","syntology_url":"https://syntology.ai/paper/2408.03281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03281"}},"official":{"repos":["c-box/structeval"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/citekit-a-modular-toolkit-for-large-language","slug":"citekit-a-modular-toolkit-for-large-language","title":"Citekit: A Modular Toolkit for Large Language Model Citation Generation","date":"2024-08-06","arxiv_id":"2408.04662","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/citekit-a-modular-toolkit-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2408.04662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04662"}},"official":{"repos":["sjj1017/citekit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ullme-a-unified-framework-for-large-language","slug":"ullme-a-unified-framework-for-large-language","title":"ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning","date":"2024-08-06","arxiv_id":"2408.03402","repositories_listed":1,"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":0,"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/ullme-a-unified-framework-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2408.03402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03402"}},"official":{"repos":["nlp-uoregon/ullme"],"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/2408-02503","slug":"2408-02503","title":"UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model","date":"2024-08-05","arxiv_id":"2408.02503","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02544","slug":"2408-02544","title":"Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions","date":"2024-08-05","arxiv_id":"2408.02544","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-02544#ran","syntology_url":"https://syntology.ai/paper/2408.02544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02544"}},"official":{"repos":["xbmxb/EnvDistraction"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/xmainframe-a-large-language-model-for","slug":"xmainframe-a-large-language-model-for","title":"XMainframe: A Large Language Model for Mainframe Modernization","date":"2024-08-05","arxiv_id":"2408.04660","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01096","slug":"2408-01096","title":"Six Dragons Fly Again: Reviving 15th-Century Korean Court Music with Transformers and Novel Encoding","date":"2024-08-02","arxiv_id":"2408.01096","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00357","slug":"2408-00357","title":"DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model","date":"2024-08-01","arxiv_id":"2408.00357","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00624","slug":"2408-00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","date":"2024-08-01","arxiv_id":"2408.00624","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00690","slug":"2408-00690","title":"Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning","date":"2024-08-01","arxiv_id":"2408.00690","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00764","slug":"2408-00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","date":"2024-08-01","arxiv_id":"2408.00764","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/2408-00764#ran","syntology_url":"https://syntology.ai/paper/2408.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00764"}},"official":{"repos":["lazychih114/AgentGen-Reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/2407-21757","slug":"2407-21757","title":"Learning Video Context as Interleaved Multimodal Sequences","date":"2024-07-31","arxiv_id":"2407.21757","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/2407-21757#ran","syntology_url":"https://syntology.ai/paper/2407.21757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21757"}},"official":{"repos":["showlab/movieseq"],"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":["official"]}}},{"url":"/paper/2408-00113","slug":"2408-00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","date":"2024-07-31","arxiv_id":"2408.00113","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"9 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-00113#ran","syntology_url":"https://syntology.ai/paper/2408.00113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00113"}},"official":{"repos":["adamkarvonen/SAE_BoardGameEval"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2407-21170","slug":"2407-21170","title":"Decomposed Prompting to Answer Questions on a Course Discussion Board","date":"2024-07-30","arxiv_id":"2407.21170","repositories_listed":1,"syntology":null},{"url":"/paper/cleft-language-image-contrastive-learning","slug":"cleft-language-image-contrastive-learning","title":"CLEFT: Language-Image Contrastive Learning with Efficient Large Language Model and Prompt Fine-Tuning","date":"2024-07-30","arxiv_id":"2407.21011","repositories_listed":1,"syntology":null},{"url":"/paper/faithful-and-plausible-natural-language","slug":"faithful-and-plausible-natural-language","title":"Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach","date":"2024-07-30","arxiv_id":"2407.20899","repositories_listed":1,"syntology":null},{"url":"/paper/optimus-0-3-using-large-language-models-to","slug":"optimus-0-3-using-large-language-models-to","title":"OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale","date":"2024-07-29","arxiv_id":"2407.19633","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/optimus-0-3-using-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2407.19633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19633"}},"official":null}}],"record_sha256":"cc9f1165262c2eca5e53c4901cbc9049b695c6d24942b3945ed72be1de4d4a70","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}