{"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/large-language-model/papers/16","list_of":"/task/large-language-model","task":"Large Language Model","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":16,"pages_in_order":61,"rows_per_page":100,"rows":[1501,1600],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model","prev":"/task/large-language-model/papers/15","next":"/task/large-language-model/papers/17","papers":[{"url":"/paper/diffagent-fast-and-accurate-text-to-image-api","slug":"diffagent-fast-and-accurate-text-to-image-api","title":"DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model","date":"2024-03-31","arxiv_id":"2404.01342","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-the-power-of-large-language-model","slug":"harnessing-the-power-of-large-language-model","title":"Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing","date":"2024-03-31","arxiv_id":"2404.00589","repositories_listed":1,"syntology":null},{"url":"/paper/wavllm-towards-robust-and-adaptive-speech","slug":"wavllm-towards-robust-and-adaptive-speech","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","date":"2024-03-31","arxiv_id":"2404.00656","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wavllm-towards-robust-and-adaptive-speech#ran","syntology_url":"https://syntology.ai/paper/2404.00656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00656"}},"official":{"repos":["microsoft/speecht5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-vision-language-models-understand-compound","slug":"do-vision-language-models-understand-compound","title":"Do Vision-Language Models Understand Compound Nouns?","date":"2024-03-30","arxiv_id":"2404.00419","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-vision-language-models-understand-compound#ran","syntology_url":"https://syntology.ai/paper/2404.00419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00419"}},"official":{"repos":["sonalkum/compun"],"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/enhancing-content-based-recommendation-via","slug":"enhancing-content-based-recommendation-via","title":"Enhancing Content-based Recommendation via Large Language Model","date":"2024-03-30","arxiv_id":"2404.00236","repositories_listed":1,"syntology":null},{"url":"/paper/eventground-narrative-reasoning-by-grounding","slug":"eventground-narrative-reasoning-by-grounding","title":"EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs","date":"2024-03-30","arxiv_id":"2404.00209","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-driven-game-engines-on-large","slug":"instruction-driven-game-engines-on-large","title":"Instruction-Driven Game Engines on Large Language Models","date":"2024-03-30","arxiv_id":"2404.00276","repositories_listed":1,"syntology":null},{"url":"/paper/your-co-workers-matter-evaluating","slug":"your-co-workers-matter-evaluating","title":"Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World","date":"2024-03-30","arxiv_id":"2404.00246","repositories_listed":1,"syntology":null},{"url":"/paper/draw-and-understand-leveraging-visual-prompts","slug":"draw-and-understand-leveraging-visual-prompts","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","date":"2024-03-29","arxiv_id":"2403.20271","repositories_listed":1,"syntology":null},{"url":"/paper/mango-a-benchmark-for-evaluating-mapping-and","slug":"mango-a-benchmark-for-evaluating-mapping-and","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","date":"2024-03-29","arxiv_id":"2403.19913","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/mango-a-benchmark-for-evaluating-mapping-and#ran","syntology_url":"https://syntology.ai/paper/2403.19913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19913"}},"official":{"repos":["oaklight/mango"],"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/change-agent-towards-interactive","slug":"change-agent-towards-interactive","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","date":"2024-03-28","arxiv_id":"2403.19646","repositories_listed":1,"syntology":null},{"url":"/paper/evolving-assembly-code-in-an-adversarial","slug":"evolving-assembly-code-in-an-adversarial","title":"Evolving Assembly Code in an Adversarial Environment","date":"2024-03-28","arxiv_id":"2403.19489","repositories_listed":1,"syntology":null},{"url":"/paper/multi-frame-lightweight-efficient-vision","slug":"multi-frame-lightweight-efficient-vision","title":"Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving","date":"2024-03-28","arxiv_id":"2403.19838","repositories_listed":1,"syntology":null},{"url":"/paper/common-sense-enhanced-knowledge-based","slug":"common-sense-enhanced-knowledge-based","title":"Common Sense Enhanced Knowledge-based Recommendation with Large Language Model","date":"2024-03-27","arxiv_id":"2403.18325","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-generative-recommendation-via","slug":"enhanced-generative-recommendation-via","title":"Content-Based Collaborative Generation for Recommender Systems","date":"2024-03-27","arxiv_id":"2403.18480","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":9,"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/enhanced-generative-recommendation-via#ran","syntology_url":"https://syntology.ai/paper/2403.18480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18480"}},"official":{"repos":["junewang0614/colarec"],"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/homogeneous-tokenizer-matters-homogeneous","slug":"homogeneous-tokenizer-matters-homogeneous","title":"Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding","date":"2024-03-27","arxiv_id":"2403.18593","repositories_listed":1,"syntology":null},{"url":"/paper/nl-iti-optimizing-probing-and-intervention","slug":"nl-iti-optimizing-probing-and-intervention","title":"Non-Linear Inference Time Intervention: Improving LLM Truthfulness","date":"2024-03-27","arxiv_id":"2403.18680","repositories_listed":1,"syntology":null},{"url":"/paper/reshaping-free-text-radiology-notes-into","slug":"reshaping-free-text-radiology-notes-into","title":"Reshaping Free-Text Radiology Notes Into Structured Reports With Generative Transformers","date":"2024-03-27","arxiv_id":"2403.18938","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-recommendation-with-latent","slug":"sequential-recommendation-with-latent","title":"Sequential Recommendation with Latent Relations based on Large Language Model","date":"2024-03-27","arxiv_id":"2403.18348","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":1,"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/sequential-recommendation-with-latent#ran","syntology_url":"https://syntology.ai/paper/2403.18348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18348"}},"official":{"repos":["ysh-1998/lrd"],"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/triviahg-a-dataset-for-automatic-hint","slug":"triviahg-a-dataset-for-automatic-hint","title":"TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions","date":"2024-03-27","arxiv_id":"2403.18426","repositories_listed":1,"syntology":null},{"url":"/paper/a-foundation-model-utilizing-chest-ct-volumes","slug":"a-foundation-model-utilizing-chest-ct-volumes","title":"Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","date":"2024-03-26","arxiv_id":"2403.17834","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 4 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-foundation-model-utilizing-chest-ct-volumes#ran","syntology_url":"https://syntology.ai/paper/2403.17834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17834"}},"official":{"repos":["ibrahimethemhamamci/ct-clip"],"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","unlocated"]}}},{"url":"/paper/jmultiwoz-a-large-scale-japanese-multi-domain","slug":"jmultiwoz-a-large-scale-japanese-multi-domain","title":"JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset","date":"2024-03-26","arxiv_id":"2403.17319","repositories_listed":1,"syntology":null},{"url":"/paper/lisa-layerwise-importance-sampling-for-memory","slug":"lisa-layerwise-importance-sampling-for-memory","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","date":"2024-03-26","arxiv_id":"2403.17919","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/lisa-layerwise-importance-sampling-for-memory#ran","syntology_url":"https://syntology.ai/paper/2403.17919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17919"}},"official":{"repos":["optimalscale/lmflow"],"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/optimization-based-prompt-injection-attack-to","slug":"optimization-based-prompt-injection-attack-to","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","date":"2024-03-26","arxiv_id":"2403.17710","repositories_listed":1,"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":2,"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/optimization-based-prompt-injection-attack-to#ran","syntology_url":"https://syntology.ai/paper/2403.17710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17710"}},"official":{"repos":["shijiawenwen/judgedeceiver"],"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/aligning-with-human-judgement-the-role-of","slug":"aligning-with-human-judgement-the-role-of","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","date":"2024-03-25","arxiv_id":"2403.16950","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-with-human-judgement-the-role-of#ran","syntology_url":"https://syntology.ai/paper/2403.16950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16950"}},"official":{"repos":["cambridgeltl/pairs"],"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/cross-lingual-contextualized-phrase-retrieval","slug":"cross-lingual-contextualized-phrase-retrieval","title":"Cross-lingual Contextualized Phrase Retrieval","date":"2024-03-25","arxiv_id":"2403.16820","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"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) · 5 unverified","sample_list":"/paper/cross-lingual-contextualized-phrase-retrieval#ran","syntology_url":"https://syntology.ai/paper/2403.16820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16820"}},"official":{"repos":["ghrua/ccpr_release"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dreamlip-language-image-pre-training-with","slug":"dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","arxiv_id":"2403.17007","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dreamlip-language-image-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2403.17007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17007"}},"official":{"repos":["zyf0619sjtu/DreamLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/generation-of-asset-administration-shell-with","slug":"generation-of-asset-administration-shell-with","title":"Generation of Asset Administration Shell with Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0","date":"2024-03-25","arxiv_id":"2403.17209","repositories_listed":1,"syntology":null},{"url":"/paper/if-clip-could-talk-understanding-vision","slug":"if-clip-could-talk-understanding-vision","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","date":"2024-03-25","arxiv_id":"2403.16442","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/if-clip-could-talk-understanding-vision#ran","syntology_url":"https://syntology.ai/paper/2403.16442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16442"}},"official":{"repos":["batsresearch/ex2"],"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/leveraging-large-language-model-to-generate-a","slug":"leveraging-large-language-model-to-generate-a","title":"Leveraging Large Language Model to Generate a Novel Metaheuristic Algorithm with CRISPE Framework","date":"2024-03-25","arxiv_id":"2403.16417","repositories_listed":1,"syntology":null},{"url":"/paper/repairagent-an-autonomous-llm-based-agent-for","slug":"repairagent-an-autonomous-llm-based-agent-for","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","date":"2024-03-25","arxiv_id":"2403.17134","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":1,"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/repairagent-an-autonomous-llm-based-agent-for#ran","syntology_url":"https://syntology.ai/paper/2403.17134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17134"}},"official":{"repos":["sola-st/RepairAgent"],"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/ru22fact-optimizing-evidence-for-multilingual","slug":"ru22fact-optimizing-evidence-for-multilingual","title":"RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict","date":"2024-03-25","arxiv_id":"2403.16662","repositories_listed":1,"syntology":null},{"url":"/paper/textit-linkprompt-natural-and-universal","slug":"textit-linkprompt-natural-and-universal","title":"$\\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models","date":"2024-03-25","arxiv_id":"2403.16432","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/textit-linkprompt-natural-and-universal#ran","syntology_url":"https://syntology.ai/paper/2403.16432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16432"}},"official":{"repos":["savannahxu79/linkprompt"],"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/a-survey-on-self-supervised-pre-training-of","slug":"a-survey-on-self-supervised-pre-training-of","title":"A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective","date":"2024-03-24","arxiv_id":"2403.16137","repositories_listed":1,"syntology":null},{"url":"/paper/ghost-sentence-a-tool-for-everyday-users-to","slug":"ghost-sentence-a-tool-for-everyday-users-to","title":"Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training","date":"2024-03-23","arxiv_id":"2403.15740","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-textbf-rag-based-summarization","slug":"towards-a-textbf-rag-based-summarization","title":"Towards a RAG-based Summarization Agent for the Electron-Ion Collider","date":"2024-03-23","arxiv_id":"2403.15729","repositories_listed":1,"syntology":null},{"url":"/paper/an-exploratory-investigation-into-code","slug":"an-exploratory-investigation-into-code","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","date":"2024-03-22","arxiv_id":"2403.15230","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-evaluation-and-insights-into-1","slug":"comprehensive-evaluation-and-insights-into-1","title":"Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation","date":"2024-03-22","arxiv_id":"2403.14965","repositories_listed":1,"syntology":null},{"url":"/paper/llava-prumerge-adaptive-token-reduction-for","slug":"llava-prumerge-adaptive-token-reduction-for","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","date":"2024-03-22","arxiv_id":"2403.15388","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/llava-prumerge-adaptive-token-reduction-for#ran","syntology_url":"https://syntology.ai/paper/2403.15388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15388"}},"official":null}},{"url":"/paper/cobra-extending-mamba-to-multi-modal-large","slug":"cobra-extending-mamba-to-multi-modal-large","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","date":"2024-03-21","arxiv_id":"2403.14520","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":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/cobra-extending-mamba-to-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2403.14520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14520"}},"official":{"repos":["h-zhao1997/cobra"],"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/mmidr-teaching-large-language-model-to","slug":"mmidr-teaching-large-language-model-to","title":"MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation","date":"2024-03-21","arxiv_id":"2403.14171","repositories_listed":1,"syntology":null},{"url":"/paper/wikifactdiff-a-large-realistic-and-temporally","slug":"wikifactdiff-a-large-realistic-and-temporally","title":"WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models","date":"2024-03-21","arxiv_id":"2403.14364","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/wikifactdiff-a-large-realistic-and-temporally#ran","syntology_url":"https://syntology.ai/paper/2403.14364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14364"}},"official":{"repos":["orange-opensource/wikifactdiff"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-large-language-model-enhanced-sequential","slug":"a-large-language-model-enhanced-sequential","title":"A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation","date":"2024-03-20","arxiv_id":"2403.13574","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/a-large-language-model-enhanced-sequential#ran","syntology_url":"https://syntology.ai/paper/2403.13574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13574"}},"official":{"repos":["rucaibox/lsvcr"],"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/community-needs-and-assets-a-computational","slug":"community-needs-and-assets-a-computational","title":"Community Needs and Assets: A Computational Analysis of Community Conversations","date":"2024-03-20","arxiv_id":"2403.13272","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-multi-constraint-molecular","slug":"instruction-multi-constraint-molecular","title":"Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model","date":"2024-03-20","arxiv_id":"2403.13244","repositories_listed":1,"syntology":null},{"url":"/paper/factorized-learning-assisted-with-large","slug":"factorized-learning-assisted-with-large","title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","date":"2024-03-19","arxiv_id":"2403.12556","repositories_listed":1,"syntology":null},{"url":"/paper/llm-gem-large-language-model-guided","slug":"llm-gem-large-language-model-guided","title":"LLM-GEm: Large Language Model-Guided Prediction of People’s Empathy Levels towards Newspaper Article","date":"2024-03-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-interpretable-hate-speech-detection","slug":"towards-interpretable-hate-speech-detection","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","date":"2024-03-19","arxiv_id":"2403.12403","repositories_listed":1,"syntology":null},{"url":"/paper/can-llm-augmented-autonomous-agents-cooperate","slug":"can-llm-augmented-autonomous-agents-cooperate","title":"Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot","date":"2024-03-18","arxiv_id":"2403.11381","repositories_listed":1,"syntology":null},{"url":"/paper/llm-3-large-language-model-based-task-and","slug":"llm-3-large-language-model-based-task-and","title":"LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning","date":"2024-03-18","arxiv_id":"2403.11552","repositories_listed":1,"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/llm-3-large-language-model-based-task-and#ran","syntology_url":"https://syntology.ai/paper/2403.11552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11552"}},"official":{"repos":["assassinws/llm-tamp"],"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/meta-prompting-for-automating-zero-shot","slug":"meta-prompting-for-automating-zero-shot","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","date":"2024-03-18","arxiv_id":"2403.11755","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-prompting-for-automating-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.11755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11755"}},"official":{"repos":["jmiemirza/meta-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-classics-a-study-on","slug":"revisiting-the-classics-a-study-on","title":"Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems","date":"2024-03-18","arxiv_id":"2403.11752","repositories_listed":1,"syntology":null},{"url":"/paper/subjective-aligned-dateset-and-metric-for","slug":"subjective-aligned-dateset-and-metric-for","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","date":"2024-03-18","arxiv_id":"2403.11956","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/subjective-aligned-dateset-and-metric-for#ran","syntology_url":"https://syntology.ai/paper/2403.11956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11956"}},"official":{"repos":["qmme/t2vqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/correcting-misinformation-on-social-media","slug":"correcting-misinformation-on-social-media","title":"Correcting misinformation on social media with a large language model","date":"2024-03-17","arxiv_id":"2403.11169","repositories_listed":1,"syntology":null},{"url":"/paper/selfie-self-interpretation-of-large-language","slug":"selfie-self-interpretation-of-large-language","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","date":"2024-03-16","arxiv_id":"2403.10949","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/selfie-self-interpretation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2403.10949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10949"}},"official":{"repos":["tonychenxyz/selfie"],"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/improving-medical-multi-modal-contrastive","slug":"improving-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","date":"2024-03-15","arxiv_id":"2403.10153","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"5 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/improving-medical-multi-modal-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.10153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10153"}},"official":{"repos":["ykumards/eclip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-informed-ecg-dual","slug":"large-language-model-informed-ecg-dual","title":"Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction","date":"2024-03-15","arxiv_id":"2403.10581","repositories_listed":1,"syntology":null},{"url":"/paper/are-vision-language-models-texture-or-shape","slug":"are-vision-language-models-texture-or-shape","title":"Can We Talk Models Into Seeing the World Differently?","date":"2024-03-14","arxiv_id":"2403.09193","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/are-vision-language-models-texture-or-shape#ran","syntology_url":"https://syntology.ai/paper/2403.09193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09193"}},"official":{"repos":["paulgavrikov/vlm_shapebias"],"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/what-was-your-prompt-a-remote-keylogging","slug":"what-was-your-prompt-a-remote-keylogging","title":"What Was Your Prompt? A Remote Keylogging Attack on AI Assistants","date":"2024-03-14","arxiv_id":"2403.09751","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/what-was-your-prompt-a-remote-keylogging#ran","syntology_url":"https://syntology.ai/paper/2403.09751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09751"}},"official":{"repos":["royweiss1/GPT_Keylogger"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-disfluency-detection-with-large","slug":"boosting-disfluency-detection-with-large","title":"Boosting Disfluency Detection with Large Language Model as Disfluency Generator","date":"2024-03-13","arxiv_id":"2403.08229","repositories_listed":1,"syntology":null},{"url":"/paper/coin-a-benchmark-of-continual-instruction","slug":"coin-a-benchmark-of-continual-instruction","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","date":"2024-03-13","arxiv_id":"2403.08350","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":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coin-a-benchmark-of-continual-instruction#ran","syntology_url":"https://syntology.ai/paper/2403.08350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08350"}},"official":{"repos":["zackschen/coin"],"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/do-large-language-models-solve-arc-visual","slug":"do-large-language-models-solve-arc-visual","title":"Do Large Language Models Solve ARC Visual Analogies Like People Do?","date":"2024-03-13","arxiv_id":"2403.09734","repositories_listed":1,"syntology":null},{"url":"/paper/emergence-of-social-norms-in-large-language","slug":"emergence-of-social-norms-in-large-language","title":"Emergence of Social Norms in Generative Agent Societies: Principles and Architecture","date":"2024-03-13","arxiv_id":"2403.08251","repositories_listed":1,"syntology":{"n":23,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":23,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/emergence-of-social-norms-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2403.08251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08251"}},"official":{"repos":["sxswz213/crsec"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/is-context-helpful-for-chat-translation","slug":"is-context-helpful-for-chat-translation","title":"Is Context Helpful for Chat Translation Evaluation?","date":"2024-03-13","arxiv_id":"2403.08314","repositories_listed":1,"syntology":null},{"url":"/paper/llm-assisted-light-leveraging-large-language","slug":"llm-assisted-light-leveraging-large-language","title":"LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments","date":"2024-03-13","arxiv_id":"2403.08337","repositories_listed":1,"syntology":null},{"url":"/paper/masked-generative-story-transformer-with","slug":"masked-generative-story-transformer-with","title":"Masked Generative Story Transformer with Character Guidance and Caption Augmentation","date":"2024-03-13","arxiv_id":"2403.08502","repositories_listed":1,"syntology":null},{"url":"/paper/sotopia-p-interactive-learning-of-socially","slug":"sotopia-p-interactive-learning-of-socially","title":"SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents","date":"2024-03-13","arxiv_id":"2403.08715","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/sotopia-p-interactive-learning-of-socially#ran","syntology_url":"https://syntology.ai/paper/2403.08715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08715"}},"official":{"repos":["sotopia-lab/sotopia-pi"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-personalized-evaluation-of-large","slug":"towards-personalized-evaluation-of-large","title":"Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform","date":"2024-03-13","arxiv_id":"2403.08305","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-text-frozen-large-language-models-in","slug":"beyond-text-frozen-large-language-models-in","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","date":"2024-03-12","arxiv_id":"2403.07874","repositories_listed":1,"syntology":{"n":26,"n_ran":17,"n_constructed":0,"n_ran_checked":6,"n_instrument":11,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":26,"phrase":"17 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; 11 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/beyond-text-frozen-large-language-models-in#ran","syntology_url":"https://syntology.ai/paper/2403.07874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07874"}},"official":{"repos":["zh460045050/v2l-tokenizer"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/characterization-of-large-language-model","slug":"characterization-of-large-language-model","title":"Characterization of Large Language Model Development in the Datacenter","date":"2024-03-12","arxiv_id":"2403.07648","repositories_listed":1,"syntology":null},{"url":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","repositories_listed":1,"syntology":null},{"url":"/paper/premonition-using-generative-models-to","slug":"premonition-using-generative-models-to","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning","date":"2024-03-12","arxiv_id":"2403.07356","repositories_listed":1,"syntology":null},{"url":"/paper/svd-llm-truncation-aware-singular-value","slug":"svd-llm-truncation-aware-singular-value","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","date":"2024-03-12","arxiv_id":"2403.07378","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/svd-llm-truncation-aware-singular-value#ran","syntology_url":"https://syntology.ai/paper/2403.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07378"}},"official":{"repos":["aiot-mlsys-lab/svd-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/conspemollm-conspiracy-theory-detection-using","slug":"conspemollm-conspiracy-theory-detection-using","title":"ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model","date":"2024-03-11","arxiv_id":"2403.06765","repositories_listed":1,"syntology":null},{"url":"/paper/drivedreamer-2-llm-enhanced-world-models-for","slug":"drivedreamer-2-llm-enhanced-world-models-for","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","date":"2024-03-11","arxiv_id":"2403.06845","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/drivedreamer-2-llm-enhanced-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.06845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06845"}},"official":null}},{"url":"/paper/exploring-large-language-models-and","slug":"exploring-large-language-models-and","title":"Exploring Large Language Models and Hierarchical Frameworks for Classification of Large Unstructured Legal Documents","date":"2024-03-11","arxiv_id":"2403.06872","repositories_listed":1,"syntology":null},{"url":"/paper/from-english-to-asic-hardware-implementation","slug":"from-english-to-asic-hardware-implementation","title":"From English to ASIC: Hardware Implementation with Large Language Model","date":"2024-03-11","arxiv_id":"2403.07039","repositories_listed":1,"syntology":null},{"url":"/paper/monitoring-ai-modified-content-at-scale-a","slug":"monitoring-ai-modified-content-at-scale-a","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","date":"2024-03-11","arxiv_id":"2403.07183","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/monitoring-ai-modified-content-at-scale-a#ran","syntology_url":"https://syntology.ai/paper/2403.07183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07183"}},"official":{"repos":["Weixin-Liang/Mapping-the-Increasing-Use-of-LLMs-in-Scientific-Papers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/smart-infinity-fast-large-language-model","slug":"smart-infinity-fast-large-language-model","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","date":"2024-03-11","arxiv_id":"2403.06664","repositories_listed":1,"syntology":null},{"url":"/paper/trad-enhancing-llm-agents-with-step-wise","slug":"trad-enhancing-llm-agents-with-step-wise","title":"TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision","date":"2024-03-10","arxiv_id":"2403.06221","repositories_listed":1,"syntology":null},{"url":"/paper/tapilot-crossing-benchmarking-and-evolving","slug":"tapilot-crossing-benchmarking-and-evolving","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","date":"2024-03-08","arxiv_id":"2403.05307","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tapilot-crossing-benchmarking-and-evolving#ran","syntology_url":"https://syntology.ai/paper/2403.05307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05307"}},"official":{"repos":["tapilot-crossing/tapilot_code"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/do-large-language-model-understand-multi","slug":"do-large-language-model-understand-multi","title":"Do Large Language Model Understand Multi-Intent Spoken Language ?","date":"2024-03-07","arxiv_id":"2403.04481","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-biases-in-context-dependent-health","slug":"evaluating-biases-in-context-dependent-health","title":"Evaluating Biases in Context-Dependent Health Questions","date":"2024-03-07","arxiv_id":"2403.04858","repositories_listed":1,"syntology":null},{"url":"/paper/self-evaluation-of-large-language-model-based","slug":"self-evaluation-of-large-language-model-based","title":"Self-Evaluation of Large Language Model based on Glass-box Features","date":"2024-03-07","arxiv_id":"2403.04222","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-chest-x-ray-datasets-with-privacy","slug":"enhancing-chest-x-ray-datasets-with-privacy","title":"Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classification","date":"2024-03-06","arxiv_id":"2403.04024","repositories_listed":1,"syntology":null},{"url":"/paper/generative-news-recommendation","slug":"generative-news-recommendation","title":"Generative News Recommendation","date":"2024-03-06","arxiv_id":"2403.03424","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm","slug":"an-empirical-study-of-llm-as-a-judge-for-llm","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","date":"2024-03-05","arxiv_id":"2403.02839","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm#ran","syntology_url":"https://syntology.ai/paper/2403.02839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02839"}},"official":{"repos":["huihuichyan/unlimitedjudge"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/android-in-the-zoo-chain-of-action-thought","slug":"android-in-the-zoo-chain-of-action-thought","title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","date":"2024-03-05","arxiv_id":"2403.02713","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/android-in-the-zoo-chain-of-action-thought#ran","syntology_url":"https://syntology.ai/paper/2403.02713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02713"}},"official":{"repos":["imnearth/coat"],"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/causal-walk-debiasing-multi-hop-fact","slug":"causal-walk-debiasing-multi-hop-fact","title":"Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment","date":"2024-03-05","arxiv_id":"2403.02698","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/causal-walk-debiasing-multi-hop-fact#ran","syntology_url":"https://syntology.ai/paper/2403.02698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02698"}},"official":{"repos":["zcccccz/causalwalk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dppa-pruning-method-for-large-language-model","slug":"dppa-pruning-method-for-large-language-model","title":"DPPA: Pruning Method for Large Language Model to Model Merging","date":"2024-03-05","arxiv_id":"2403.02799","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-and-optimizing-educational-content","slug":"evaluating-and-optimizing-educational-content","title":"Evaluating and Optimizing Educational Content with Large Language Model Judgments","date":"2024-03-05","arxiv_id":"2403.02795","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/evaluating-and-optimizing-educational-content#ran","syntology_url":"https://syntology.ai/paper/2403.02795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02795"}},"official":{"repos":["StanfordAI4HI/ed-expert-simulator"],"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/multi-modal-instruction-tuned-llms-with-fine","slug":"multi-modal-instruction-tuned-llms-with-fine","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","date":"2024-03-05","arxiv_id":"2403.02969","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":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) · 3 unverified","sample_list":"/paper/multi-modal-instruction-tuned-llms-with-fine#ran","syntology_url":"https://syntology.ai/paper/2403.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02969"}},"official":{"repos":["jwh97nn/anyref"],"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/knowphish-large-language-models-meet","slug":"knowphish-large-language-models-meet","title":"KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection","date":"2024-03-04","arxiv_id":"2403.02253","repositories_listed":1,"syntology":null},{"url":"/paper/llm-vs-lawyers-identifying-a-subset-of","slug":"llm-vs-lawyers-identifying-a-subset-of","title":"LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset","date":"2024-03-04","arxiv_id":"2403.04791","repositories_listed":1,"syntology":null},{"url":"/paper/offlandat-a-community-based-implicit","slug":"offlandat-a-community-based-implicit","title":"OffensiveLang: A Community Based Implicit Offensive Language Dataset","date":"2024-03-04","arxiv_id":"2403.02472","repositories_listed":1,"syntology":null},{"url":"/paper/syllabusqa-a-course-logistics-question","slug":"syllabusqa-a-course-logistics-question","title":"SyllabusQA: A Course Logistics Question Answering Dataset","date":"2024-03-03","arxiv_id":"2403.14666","repositories_listed":1,"syntology":null},{"url":"/paper/a-cross-modal-approach-to-silent-speech-with","slug":"a-cross-modal-approach-to-silent-speech-with","title":"A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition","date":"2024-03-02","arxiv_id":"2403.05583","repositories_listed":1,"syntology":null},{"url":"/paper/chaining-thoughts-and-llms-to-learn-dna","slug":"chaining-thoughts-and-llms-to-learn-dna","title":"Chaining thoughts and LLMs to learn DNA structural biophysics","date":"2024-03-02","arxiv_id":"2403.01332","repositories_listed":1,"syntology":null},{"url":"/paper/dmoerm-recipes-of-mixture-of-experts-for","slug":"dmoerm-recipes-of-mixture-of-experts-for","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","date":"2024-03-02","arxiv_id":"2403.01197","repositories_listed":1,"syntology":null}],"record_sha256":"bdf3d276d15d9a57a64d722681c1da8fe22a49dc5bce02611dd3a0a27e1988e8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}