{"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/31","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":31,"pages_in_order":142,"rows_per_page":100,"rows":[3001,3100],"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/30","next":"/task/language-modeling/papers/32","papers":[{"url":"/paper/pretraining-vision-language-model-for","slug":"pretraining-vision-language-model-for","title":"Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays","date":"2024-02-14","arxiv_id":"2402.08966","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-the-authoring-of-autotutors-with","slug":"scaling-the-authoring-of-autotutors-with","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","date":"2024-02-14","arxiv_id":"2402.09216","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 6 unverified","sample_list":"/paper/scaling-the-authoring-of-autotutors-with#ran","syntology_url":"https://syntology.ai/paper/2402.09216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09216"}},"official":{"repos":["eth-lre/mwptutor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-me-more-towards-implicit-user-intention","slug":"tell-me-more-towards-implicit-user-intention","title":"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents","date":"2024-02-14","arxiv_id":"2402.09205","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tell-me-more-towards-implicit-user-intention#ran","syntology_url":"https://syntology.ai/paper/2402.09205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09205"}},"official":{"repos":["hbx-hbx/mistral-interact"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-and-controlling-instruction-in","slug":"measuring-and-controlling-instruction-in","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","date":"2024-02-13","arxiv_id":"2402.10962","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/measuring-and-controlling-instruction-in#ran","syntology_url":"https://syntology.ai/paper/2402.10962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10962"}},"official":{"repos":["likenneth/persona_drift"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/punctuation-restoration-improves-structure","slug":"punctuation-restoration-improves-structure","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","date":"2024-02-13","arxiv_id":"2402.08382","repositories_listed":1,"syntology":null},{"url":"/paper/verified-multi-step-synthesis-using-large","slug":"verified-multi-step-synthesis-using-large","title":"VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search","date":"2024-02-13","arxiv_id":"2402.08147","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/verified-multi-step-synthesis-using-large#ran","syntology_url":"https://syntology.ai/paper/2402.08147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08147"}},"official":{"repos":["namin/llm-verified-with-monte-carlo-tree-search"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visually-dehallucinative-instruction","slug":"visually-dehallucinative-instruction","title":"Visually Dehallucinative Instruction Generation","date":"2024-02-13","arxiv_id":"2402.08348","repositories_listed":1,"syntology":null},{"url":"/paper/breakgpt-a-large-language-model-with-multi","slug":"breakgpt-a-large-language-model-with-multi","title":"BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection","date":"2024-02-12","arxiv_id":"2402.07536","repositories_listed":1,"syntology":null},{"url":"/paper/careless-whisper-speech-to-text-hallucination","slug":"careless-whisper-speech-to-text-hallucination","title":"Careless Whisper: Speech-to-Text Hallucination Harms","date":"2024-02-12","arxiv_id":"2402.08021","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-of-thoughts-chain-of-thought","slug":"diffusion-of-thoughts-chain-of-thought","title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","date":"2024-02-12","arxiv_id":"2402.07754","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-of-thoughts-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2402.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07754"}},"official":{"repos":["hkunlp/diffusion-of-thoughts"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wildfiregpt-tailored-large-language-model-for","slug":"wildfiregpt-tailored-large-language-model-for","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","date":"2024-02-12","arxiv_id":"2402.07877","repositories_listed":1,"syntology":null},{"url":"/paper/graphtranslator-aligning-graph-model-to-large","slug":"graphtranslator-aligning-graph-model-to-large","title":"GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks","date":"2024-02-11","arxiv_id":"2402.07197","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graphtranslator-aligning-graph-model-to-large#ran","syntology_url":"https://syntology.ai/paper/2402.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07197"}},"official":{"repos":["alibaba/graphtranslator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperbert-mixing-hypergraph-aware-layers-with","slug":"hyperbert-mixing-hypergraph-aware-layers-with","title":"HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs","date":"2024-02-11","arxiv_id":"2402.07309","repositories_listed":1,"syntology":null},{"url":"/paper/open-ended-vqa-benchmarking-of-vision","slug":"open-ended-vqa-benchmarking-of-vision","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","date":"2024-02-11","arxiv_id":"2402.07270","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":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) · 0 unverified","sample_list":"/paper/open-ended-vqa-benchmarking-of-vision#ran","syntology_url":"https://syntology.ai/paper/2402.07270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07270"}},"official":{"repos":["lmb-freiburg/ovqa"],"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/using-large-language-models-for-student-code","slug":"using-large-language-models-for-student-code","title":"Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education","date":"2024-02-11","arxiv_id":"2402.07081","repositories_listed":1,"syntology":null},{"url":"/paper/chemllm-a-chemical-large-language-model","slug":"chemllm-a-chemical-large-language-model","title":"ChemLLM: A Chemical Large Language Model","date":"2024-02-10","arxiv_id":"2402.06852","repositories_listed":1,"syntology":null},{"url":"/paper/urbankgent-a-unified-large-language-model","slug":"urbankgent-a-unified-large-language-model","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","date":"2024-02-10","arxiv_id":"2402.06861","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/urbankgent-a-unified-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.06861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06861"}},"official":{"repos":["usail-hkust/urbankgent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/aya-dataset-an-open-access-collection-for","slug":"aya-dataset-an-open-access-collection-for","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","date":"2024-02-09","arxiv_id":"2402.06619","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-regularized-token-level-policy","slug":"entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","arxiv_id":"2402.06700","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entropy-regularized-token-level-policy#ran","syntology_url":"https://syntology.ai/paper/2402.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06700"}},"official":{"repos":["morning9393/etpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-sentence-completion-with-a","slug":"language-model-sentence-completion-with-a","title":"Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method","date":"2024-02-09","arxiv_id":"2402.06125","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-model-sentence-completion-with-a#ran","syntology_url":"https://syntology.ai/paper/2402.06125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06125"}},"official":{"repos":["joshua-zingale/plug-and-play-rst-ctg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-efficacy-of-eviction-policy-for-key","slug":"on-the-efficacy-of-eviction-policy-for-key","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","date":"2024-02-09","arxiv_id":"2402.06262","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-efficacy-of-eviction-policy-for-key#ran","syntology_url":"https://syntology.ai/paper/2402.06262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06262"}},"official":{"repos":["drsy/easykv"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/screenagent-a-vision-language-model-driven","slug":"screenagent-a-vision-language-model-driven","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","date":"2024-02-09","arxiv_id":"2402.07945","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/screenagent-a-vision-language-model-driven#ran","syntology_url":"https://syntology.ai/paper/2402.07945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07945"}},"official":{"repos":["niuzaisheng/screenagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-weakness-of-large-language","slug":"understanding-the-weakness-of-large-language","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","date":"2024-02-09","arxiv_id":"2402.06596","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":4,"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/understanding-the-weakness-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.06596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06596"}},"official":{"repos":["androidarenaagent/androidarena"],"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/editable-scene-simulation-for-autonomous","slug":"editable-scene-simulation-for-autonomous","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","date":"2024-02-08","arxiv_id":"2402.05746","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":4,"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/editable-scene-simulation-for-autonomous#ran","syntology_url":"https://syntology.ai/paper/2402.05746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05746"}},"official":{"repos":["yifanlu0227/chatsim"],"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/sphinx-x-scaling-data-and-parameters-for-a","slug":"sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","arxiv_id":"2402.05935","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sphinx-x-scaling-data-and-parameters-for-a#ran","syntology_url":"https://syntology.ai/paper/2402.05935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05935"}},"official":{"repos":["alpha-vllm/llama2-accessory"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spirit-lm-interleaved-spoken-and-written","slug":"spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","arxiv_id":"2402.05755","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/spirit-lm-interleaved-spoken-and-written#ran","syntology_url":"https://syntology.ai/paper/2402.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05755"}},"official":{"repos":["facebookresearch/spiritlm"],"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/apiq-finetuning-of-2-bit-quantized-large","slug":"apiq-finetuning-of-2-bit-quantized-large","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","date":"2024-02-07","arxiv_id":"2402.05147","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/apiq-finetuning-of-2-bit-quantized-large#ran","syntology_url":"https://syntology.ai/paper/2402.05147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05147"}},"official":{"repos":["baohaoliao/apiq"],"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/can-large-language-model-agents-simulate","slug":"can-large-language-model-agents-simulate","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","date":"2024-02-07","arxiv_id":"2402.04559","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/can-large-language-model-agents-simulate#ran","syntology_url":"https://syntology.ai/paper/2402.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04559"}},"official":{"repos":["camel-ai/agent-trust"],"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/codeit-self-improving-language-models-with","slug":"codeit-self-improving-language-models-with","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","date":"2024-02-07","arxiv_id":"2402.04858","repositories_listed":1,"syntology":{"n":41,"n_ran":32,"n_constructed":4,"n_ran_checked":10,"n_instrument":22,"n_unverified":9,"n_honours":4,"n_violates":2,"n_no_contract":4,"n_pointer_only":41,"phrase":"32 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 2 violated, 4 with no contract checked; 22 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/codeit-self-improving-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2402.04858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04858"}},"official":{"repos":["Qualcomm-AI-research/codeit"],"state":"official (archive's flag): 32 ran","n_ran":32,"n_constructed":4,"n_ran_no_instrument_failure":10,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/structure-informed-protein-language-model","slug":"structure-informed-protein-language-model","title":"Structure-Informed Protein Language Model","date":"2024-02-07","arxiv_id":"2402.05856","repositories_listed":1,"syntology":null},{"url":"/paper/sumrec-a-framework-for-recommendation-using","slug":"sumrec-a-framework-for-recommendation-using","title":"SumRec: A Framework for Recommendation using Open-Domain Dialogue","date":"2024-02-07","arxiv_id":"2402.04523","repositories_listed":1,"syntology":null},{"url":"/paper/2402-03766","slug":"2402-03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","date":"2024-02-06","arxiv_id":"2402.03766","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2402-03766#ran","syntology_url":"https://syntology.ai/paper/2402.03766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03766"}},"official":{"repos":["meituan-automl/mobilevlm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/anytool-self-reflective-hierarchical-agents","slug":"anytool-self-reflective-hierarchical-agents","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","date":"2024-02-06","arxiv_id":"2402.04253","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/anytool-self-reflective-hierarchical-agents#ran","syntology_url":"https://syntology.ai/paper/2402.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04253"}},"official":{"repos":["dyabel/anytool"],"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/personalized-language-modeling-from","slug":"personalized-language-modeling-from","title":"Personalized Language Modeling from Personalized Human Feedback","date":"2024-02-06","arxiv_id":"2402.05133","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/personalized-language-modeling-from#ran","syntology_url":"https://syntology.ai/paper/2402.05133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05133"}},"official":{"repos":["humainlab/personalized_rlhf"],"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/positive-concave-deep-equilibrium-models","slug":"positive-concave-deep-equilibrium-models","title":"Positive concave deep equilibrium models","date":"2024-02-06","arxiv_id":"2402.04029","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-synonym-bert-based-adversarial","slug":"arabic-synonym-bert-based-adversarial","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","date":"2024-02-05","arxiv_id":"2402.03477","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-distilling-medication","slug":"large-language-model-distilling-medication","title":"Large Language Model Distilling Medication Recommendation Model","date":"2024-02-05","arxiv_id":"2402.02803","repositories_listed":1,"syntology":null},{"url":"/paper/racer-an-llm-powered-methodology-for-scalable","slug":"racer-an-llm-powered-methodology-for-scalable","title":"RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews","date":"2024-02-05","arxiv_id":"2402.02656","repositories_listed":1,"syntology":null},{"url":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skill-set-optimization-reinforcing-language#ran","syntology_url":"https://syntology.ai/paper/2402.03244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03244"}},"official":{"repos":["allenai/sso"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/texshape-information-theoretic-sentence","slug":"texshape-information-theoretic-sentence","title":"TexShape: Information Theoretic Sentence Embedding for Language Models","date":"2024-02-05","arxiv_id":"2402.05132","repositories_listed":1,"syntology":null},{"url":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gerea-question-aware-prompt-captions-for#ran","syntology_url":"https://syntology.ai/paper/2402.02503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02503"}},"official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/glape-gold-label-agnostic-prompt-evaluation","slug":"glape-gold-label-agnostic-prompt-evaluation","title":"GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model","date":"2024-02-04","arxiv_id":"2402.02408","repositories_listed":1,"syntology":null},{"url":"/paper/kicgpt-large-language-model-with-knowledge-in","slug":"kicgpt-large-language-model-with-knowledge-in","title":"KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion","date":"2024-02-04","arxiv_id":"2402.02389","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kicgpt-large-language-model-with-knowledge-in#ran","syntology_url":"https://syntology.ai/paper/2402.02389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02389"}},"official":{"repos":["weiyanbin1999/kicgpt"],"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","unlocated"]}}},{"url":"/paper/lhrs-bot-empowering-remote-sensing-with-vgi","slug":"lhrs-bot-empowering-remote-sensing-with-vgi","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","date":"2024-02-04","arxiv_id":"2402.02544","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lhrs-bot-empowering-remote-sensing-with-vgi#ran","syntology_url":"https://syntology.ai/paper/2402.02544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02544"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selecting-large-language-model-to-fine-tune","slug":"selecting-large-language-model-to-fine-tune","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","date":"2024-02-04","arxiv_id":"2402.02314","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selecting-large-language-model-to-fine-tune#ran","syntology_url":"https://syntology.ai/paper/2402.02314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02314"}},"official":null}},{"url":"/paper/anthroscore-a-computational-linguistic","slug":"anthroscore-a-computational-linguistic","title":"AnthroScore: A Computational Linguistic Measure of Anthropomorphism","date":"2024-02-03","arxiv_id":"2402.02056","repositories_listed":1,"syntology":null},{"url":"/paper/apiserve-efficient-api-support-for-large","slug":"apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","arxiv_id":"2402.01869","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/apiserve-efficient-api-support-for-large#ran","syntology_url":"https://syntology.ai/paper/2402.01869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01869"}},"official":{"repos":["wuklab/infercept"],"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/audio-flamingo-a-novel-audio-language-model","slug":"audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","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":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}},"official":{"repos":["NVIDIA/audio-flamingo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/decoding-speculative-decoding","slug":"decoding-speculative-decoding","title":"Decoding Speculative Decoding","date":"2024-02-02","arxiv_id":"2402.01528","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decoding-speculative-decoding#ran","syntology_url":"https://syntology.ai/paper/2402.01528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01528"}},"official":{"repos":["uw-mad-dash/decoding-speculative-decoding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/interpretation-of-intracardiac-electrograms","slug":"interpretation-of-intracardiac-electrograms","title":"Interpretation of Intracardiac Electrograms Through Textual Representations","date":"2024-02-02","arxiv_id":"2402.01115","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-role-of-proxy-rewards-in","slug":"rethinking-the-role-of-proxy-rewards-in","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","date":"2024-02-02","arxiv_id":"2402.03469","repositories_listed":1,"syntology":null},{"url":"/paper/style-vectors-for-steering-generative-large","slug":"style-vectors-for-steering-generative-large","title":"Style Vectors for Steering Generative Large Language Model","date":"2024-02-02","arxiv_id":"2402.01618","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/style-vectors-for-steering-generative-large#ran","syntology_url":"https://syntology.ai/paper/2402.01618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01618"}},"official":{"repos":["dlr-sc/style-vectors-for-steering-llms"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/blackmamba-mixture-of-experts-for-state-space","slug":"blackmamba-mixture-of-experts-for-state-space","title":"BlackMamba: Mixture of Experts for State-Space Models","date":"2024-02-01","arxiv_id":"2402.01771","repositories_listed":1,"syntology":null},{"url":"/paper/croissantllm-a-truly-bilingual-french-english","slug":"croissantllm-a-truly-bilingual-french-english","title":"CroissantLLM: A Truly Bilingual French-English Language Model","date":"2024-02-01","arxiv_id":"2402.00786","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"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) · 2 unverified","sample_list":"/paper/croissantllm-a-truly-bilingual-french-english#ran","syntology_url":"https://syntology.ai/paper/2402.00786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00786"}},"official":{"repos":["manuelfay/llm-data-hub"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llms-learn-governing-principles-of-dynamical","slug":"llms-learn-governing-principles-of-dynamical","title":"LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law","date":"2024-02-01","arxiv_id":"2402.00795","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llms-learn-governing-principles-of-dynamical#ran","syntology_url":"https://syntology.ai/paper/2402.00795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00795"}},"official":{"repos":["AntonioLiu97/llmICL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-embodied-interactive-agent-for","slug":"multimodal-embodied-interactive-agent-for","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","date":"2024-02-01","arxiv_id":"2402.00290","repositories_listed":1,"syntology":null},{"url":"/paper/non-exchangeable-conformal-language","slug":"non-exchangeable-conformal-language","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","date":"2024-02-01","arxiv_id":"2402.00707","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/non-exchangeable-conformal-language#ran","syntology_url":"https://syntology.ai/paper/2402.00707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00707"}},"official":{"repos":["kaleidophon/non-exchangeable-conformal-language-generation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pap-rec-personalized-automatic-prompt-for","slug":"pap-rec-personalized-automatic-prompt-for","title":"PAP-REC: Personalized Automatic Prompt for Recommendation Language Model","date":"2024-02-01","arxiv_id":"2402.00284","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-transformers-with-dynamic-halt","slug":"recurrent-transformers-with-dynamic-halt","title":"Investigating Recurrent Transformers with Dynamic Halt","date":"2024-02-01","arxiv_id":"2402.00976","repositories_listed":1,"syntology":null},{"url":"/paper/superfiltering-weak-to-strong-data-filtering","slug":"superfiltering-weak-to-strong-data-filtering","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","date":"2024-02-01","arxiv_id":"2402.00530","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/superfiltering-weak-to-strong-data-filtering#ran","syntology_url":"https://syntology.ai/paper/2402.00530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00530"}},"official":{"repos":["tianyi-lab/superfiltering"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/when-benchmarks-are-targets-revealing-the","slug":"when-benchmarks-are-targets-revealing-the","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","date":"2024-02-01","arxiv_id":"2402.01781","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-benchmarks-are-targets-revealing-the#ran","syntology_url":"https://syntology.ai/paper/2402.01781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01781"}},"official":{"repos":["national-center-for-ai-saudi-arabia/lm-evaluation-harness"],"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/assertion-detection-large-language-model-in","slug":"assertion-detection-large-language-model-in","title":"Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning","date":"2024-01-31","arxiv_id":"2401.17602","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-template-based-and-template-free","slug":"comparing-template-based-and-template-free","title":"Comparing Template-based and Template-free Language Model Probing","date":"2024-01-31","arxiv_id":"2402.00123","repositories_listed":1,"syntology":null},{"url":"/paper/dolma-an-open-corpus-of-three-trillion-tokens","slug":"dolma-an-open-corpus-of-three-trillion-tokens","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","date":"2024-01-31","arxiv_id":"2402.00159","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dolma-an-open-corpus-of-three-trillion-tokens#ran","syntology_url":"https://syntology.ai/paper/2402.00159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00159"}},"official":{"repos":["allenai/dolma"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enclap-combining-neural-audio-codec-and-audio","slug":"enclap-combining-neural-audio-codec-and-audio","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","date":"2024-01-31","arxiv_id":"2401.17690","repositories_listed":1,"syntology":null},{"url":"/paper/lorec-large-language-model-for-robust","slug":"lorec-large-language-model-for-robust","title":"LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks","date":"2024-01-31","arxiv_id":"2401.17723","repositories_listed":1,"syntology":null},{"url":"/paper/earthgpt-a-universal-multi-modal-large","slug":"earthgpt-a-universal-multi-modal-large","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","date":"2024-01-30","arxiv_id":"2401.16822","repositories_listed":1,"syntology":null},{"url":"/paper/gradient-based-language-model-red-teaming","slug":"gradient-based-language-model-red-teaming","title":"Gradient-Based Language Model Red Teaming","date":"2024-01-30","arxiv_id":"2401.16656","repositories_listed":1,"syntology":null},{"url":"/paper/llamp-large-language-model-made-powerful-for","slug":"llamp-large-language-model-made-powerful-for","title":"LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation","date":"2024-01-30","arxiv_id":"2401.17244","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/llamp-large-language-model-made-powerful-for#ran","syntology_url":"https://syntology.ai/paper/2401.17244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17244"}},"official":{"repos":["chiang-yuan/llamp"],"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/a-linguistic-comparison-between-human-and","slug":"a-linguistic-comparison-between-human-and","title":"A Linguistic Comparison between Human and ChatGPT-Generated Conversations","date":"2024-01-29","arxiv_id":"2401.16587","repositories_listed":1,"syntology":null},{"url":"/paper/fakeclaim-a-multiple-platform-driven-dataset","slug":"fakeclaim-a-multiple-platform-driven-dataset","title":"FakeClaim: A Multiple Platform-driven Dataset for Identification of Fake News on 2023 Israel-Hamas War","date":"2024-01-29","arxiv_id":"2401.16625","repositories_listed":1,"syntology":null},{"url":"/paper/internlm-xcomposer2-mastering-free-form-text","slug":"internlm-xcomposer2-mastering-free-form-text","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","date":"2024-01-29","arxiv_id":"2401.16420","repositories_listed":1,"syntology":null},{"url":"/paper/overcoming-the-pitfalls-of-vision-language","slug":"overcoming-the-pitfalls-of-vision-language","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization","date":"2024-01-29","arxiv_id":"2401.15914","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/overcoming-the-pitfalls-of-vision-language#ran","syntology_url":"https://syntology.ai/paper/2401.15914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15914"}},"official":{"repos":["apple/ml-ogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/textual-entailment-for-effective-triple","slug":"textual-entailment-for-effective-triple","title":"Textual Entailment for Effective Triple Validation in Object Prediction","date":"2024-01-29","arxiv_id":"2401.16293","repositories_listed":1,"syntology":null},{"url":"/paper/contextualization-distillation-from-large","slug":"contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","arxiv_id":"2402.01729","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contextualization-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2402.01729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01729"}},"official":{"repos":["david-li0406/contextulization-distillation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/protagents-protein-discovery-via-large","slug":"protagents-protein-discovery-via-large","title":"ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning","date":"2024-01-27","arxiv_id":"2402.04268","repositories_listed":1,"syntology":null},{"url":"/paper/eagle-speculative-sampling-requires","slug":"eagle-speculative-sampling-requires","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","date":"2024-01-26","arxiv_id":"2401.15077","repositories_listed":1,"syntology":null},{"url":"/paper/endowing-protein-language-models-with","slug":"endowing-protein-language-models-with","title":"Endowing Protein Language Models with Structural Knowledge","date":"2024-01-26","arxiv_id":"2401.14819","repositories_listed":1,"syntology":null},{"url":"/paper/taiyi-diffusion-xl-advancing-bilingual-text","slug":"taiyi-diffusion-xl-advancing-bilingual-text","title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","date":"2024-01-26","arxiv_id":"2401.14688","repositories_listed":1,"syntology":null},{"url":"/paper/deepseek-coder-when-the-large-language-model","slug":"deepseek-coder-when-the-large-language-model","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","date":"2024-01-25","arxiv_id":"2401.14196","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/deepseek-coder-when-the-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2401.14196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14196"}},"official":{"repos":["deepseek-ai/DeepSeek-Coder"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-natural-language-capability-of-code","slug":"improving-natural-language-capability-of-code","title":"Improving Natural Language Capability of Code Large Language Model","date":"2024-01-25","arxiv_id":"2401.14242","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-conversational","slug":"parameter-efficient-conversational","title":"Parameter-Efficient Conversational Recommender System as a Language Processing Task","date":"2024-01-25","arxiv_id":"2401.14194","repositories_listed":1,"syntology":null},{"url":"/paper/towards-3d-molecule-text-interpretation-in","slug":"towards-3d-molecule-text-interpretation-in","title":"Towards 3D Molecule-Text Interpretation in Language Models","date":"2024-01-25","arxiv_id":"2401.13923","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-3d-molecule-text-interpretation-in#ran","syntology_url":"https://syntology.ai/paper/2401.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13923"}},"official":{"repos":["lsh0520/3d-molm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-unified-approach-to-emotion-detection-and","slug":"a-unified-approach-to-emotion-detection-and","title":"A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling","date":"2024-01-24","arxiv_id":"2401.13789","repositories_listed":1,"syntology":null},{"url":"/paper/chatterbox-multi-round-multimodal-referring","slug":"chatterbox-multi-round-multimodal-referring","title":"ChatterBox: Multi-round Multimodal Referring and Grounding","date":"2024-01-24","arxiv_id":"2401.13307","repositories_listed":1,"syntology":null},{"url":"/paper/fluent-dreaming-for-language-models","slug":"fluent-dreaming-for-language-models","title":"Fluent dreaming for language models","date":"2024-01-24","arxiv_id":"2402.01702","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/fluent-dreaming-for-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.01702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01702"}},"official":{"repos":["confirm-solutions/dreamy"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/can-large-language-models-write-parallel-code","slug":"can-large-language-models-write-parallel-code","title":"Can Large Language Models Write Parallel Code?","date":"2024-01-23","arxiv_id":"2401.12554","repositories_listed":1,"syntology":{"n":19,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-large-language-models-write-parallel-code#ran","syntology_url":"https://syntology.ai/paper/2401.12554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12554"}},"official":{"repos":["parallelcodefoundry/ParEval"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dsdm-model-aware-dataset-selection-with","slug":"dsdm-model-aware-dataset-selection-with","title":"DsDm: Model-Aware Dataset Selection with Datamodels","date":"2024-01-23","arxiv_id":"2401.12926","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/dsdm-model-aware-dataset-selection-with#ran","syntology_url":"https://syntology.ai/paper/2401.12926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12926"}},"official":{"repos":["MadryLab/DsDm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/generating-unsupervised-abstractive","slug":"generating-unsupervised-abstractive","title":"Generating Zero-shot Abstractive Explanations for Rumour Verification","date":"2024-01-23","arxiv_id":"2401.12713","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-can-large-language-models-explain","slug":"how-well-can-large-language-models-explain","title":"How well can a large language model explain business processes as perceived by users?","date":"2024-01-23","arxiv_id":"2401.12846","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-language-learning-arhitectures-and","slug":"in-context-language-learning-arhitectures-and","title":"In-Context Language Learning: Architectures and Algorithms","date":"2024-01-23","arxiv_id":"2401.12973","repositories_listed":1,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/in-context-language-learning-arhitectures-and#ran","syntology_url":"https://syntology.ai/paper/2401.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12973"}},"official":{"repos":["berlino/seq_icl"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/finding-a-needle-in-the-adversarial-haystack","slug":"finding-a-needle-in-the-adversarial-haystack","title":"Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion","date":"2024-01-21","arxiv_id":"2401.11373","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-based-multi-agents-a","slug":"large-language-model-based-multi-agents-a","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","date":"2024-01-21","arxiv_id":"2402.01680","repositories_listed":1,"syntology":null},{"url":"/paper/moltailor-tailoring-chemical-molecular","slug":"moltailor-tailoring-chemical-molecular","title":"MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts","date":"2024-01-21","arxiv_id":"2401.11403","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/moltailor-tailoring-chemical-molecular#ran","syntology_url":"https://syntology.ai/paper/2401.11403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11403"}},"official":{"repos":["scir-hi/moltailor"],"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/with-greater-text-comes-greater-necessity","slug":"with-greater-text-comes-greater-necessity","title":"With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation","date":"2024-01-21","arxiv_id":"2401.11504","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/with-greater-text-comes-greater-necessity#ran","syntology_url":"https://syntology.ai/paper/2401.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11504"}},"official":{"repos":["temporarylora/temp-lora"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/embedding-ontologies-via-incoprorating","slug":"embedding-ontologies-via-incoprorating","title":"Embedding Ontologies via Incorporating Extensional and Intensional Knowledge","date":"2024-01-20","arxiv_id":"2402.01677","repositories_listed":1,"syntology":null},{"url":"/paper/image-safeguarding-reasoning-with-conditional","slug":"image-safeguarding-reasoning-with-conditional","title":"Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually","date":"2024-01-19","arxiv_id":"2401.11035","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-safeguarding-reasoning-with-conditional#ran","syntology_url":"https://syntology.ai/paper/2401.11035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11035"}},"official":{"repos":["secureaiautonomylab/conditionalvlm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mementos-a-comprehensive-benchmark-for","slug":"mementos-a-comprehensive-benchmark-for","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","date":"2024-01-19","arxiv_id":"2401.10529","repositories_listed":1,"syntology":null},{"url":"/paper/evolutionary-computation-in-the-era-of-large","slug":"evolutionary-computation-in-the-era-of-large","title":"Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap","date":"2024-01-18","arxiv_id":"2401.10034","repositories_listed":1,"syntology":null},{"url":"/paper/excuse-me-sir-your-language-model-is-leaking","slug":"excuse-me-sir-your-language-model-is-leaking","title":"Excuse me, sir? Your language model is leaking (information)","date":"2024-01-18","arxiv_id":"2401.10360","repositories_listed":1,"syntology":null}],"record_sha256":"8eae9b8018db0f98008fa108d32ca1dbd70496da5e4f0d693101f66fbb8be57c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}