{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/33","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":33,"pages_in_order":177,"rows_per_page":100,"rows":[3201,3300],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling","prev":"/task/language-modelling/papers/32","next":"/task/language-modelling/papers/34","papers":[{"url":"/paper/compression-represents-intelligence-linearly","slug":"compression-represents-intelligence-linearly","title":"Compression Represents Intelligence Linearly","date":"2024-04-15","arxiv_id":"2404.09937","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/compression-represents-intelligence-linearly#ran","syntology_url":"https://syntology.ai/paper/2404.09937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09937"}},"official":{"repos":["hkust-nlp/llm-compression-intelligence"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/constructing-benchmarks-and-interventions-for","slug":"constructing-benchmarks-and-interventions-for","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","date":"2024-04-15","arxiv_id":"2404.09971","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/constructing-benchmarks-and-interventions-for#ran","syntology_url":"https://syntology.ai/paper/2404.09971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09971"}},"official":{"repos":["technion-cs-nlp/hallucination-mitigation"],"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/in2in-leveraging-individual-information-to-1","slug":"in2in-leveraging-individual-information-to-1","title":"in2IN: Leveraging individual Information to Generate Human INteractions","date":"2024-04-15","arxiv_id":"2404.09988","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in2in-leveraging-individual-information-to-1#ran","syntology_url":"https://syntology.ai/paper/2404.09988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09988"}},"official":{"repos":["pabloruizponce/in2IN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-enhanced-visual-language","slug":"knowledge-enhanced-visual-language","title":"Knowledge-enhanced Visual-Language Pretraining for Computational Pathology","date":"2024-04-15","arxiv_id":"2404.09942","repositories_listed":1,"syntology":null},{"url":"/paper/memory-sharing-for-large-language-model-based","slug":"memory-sharing-for-large-language-model-based","title":"Memory Sharing for Large Language Model based Agents","date":"2024-04-15","arxiv_id":"2404.09982","repositories_listed":1,"syntology":null},{"url":"/paper/negation-triplet-extraction-with-syntactic","slug":"negation-triplet-extraction-with-syntactic","title":"Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency","date":"2024-04-15","arxiv_id":"2404.09830","repositories_listed":1,"syntology":null},{"url":"/paper/s-gpts-a-new-approach-to-autoregressive","slug":"s-gpts-a-new-approach-to-autoregressive","title":"σ-GPTs: A New Approach to Autoregressive Models","date":"2024-04-15","arxiv_id":"2404.09562","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-global-and-local-scene-entities","slug":"unifying-global-and-local-scene-entities","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","date":"2024-04-15","arxiv_id":"2404.09951","repositories_listed":1,"syntology":null},{"url":"/paper/customising-general-large-language-models-for-1","slug":"customising-general-large-language-models-for-1","title":"Customising General Large Language Models for Specialised Emotion Recognition Tasks","date":"2024-04-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/from-bytes-to-borsch-fine-tuning-gemma-and","slug":"from-bytes-to-borsch-fine-tuning-gemma-and","title":"From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation","date":"2024-04-14","arxiv_id":"2404.09138","repositories_listed":1,"syntology":null},{"url":"/paper/toner-type-oriented-named-entity-recognition","slug":"toner-type-oriented-named-entity-recognition","title":"ToNER: Type-oriented Named Entity Recognition with Generative Language Model","date":"2024-04-14","arxiv_id":"2404.09145","repositories_listed":1,"syntology":null},{"url":"/paper/trafficvlm-a-controllable-visual-language","slug":"trafficvlm-a-controllable-visual-language","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","date":"2024-04-14","arxiv_id":"2404.09275","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trafficvlm-a-controllable-visual-language#ran","syntology_url":"https://syntology.ai/paper/2404.09275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09275"}},"official":{"repos":["quangminhdinh/trafficvlm"],"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/llmsat-a-large-language-model-based-goal","slug":"llmsat-a-large-language-model-based-goal","title":"LLMSat: A Large Language Model-Based Goal-Oriented Agent for Autonomous Space Exploration","date":"2024-04-13","arxiv_id":"2405.01392","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-autonomous-vehicle-training-with","slug":"enhancing-autonomous-vehicle-training-with","title":"Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation","date":"2024-04-12","arxiv_id":"2404.08570","repositories_listed":1,"syntology":null},{"url":"/paper/inverse-kinematics-for-neuro-robotic-grasping","slug":"inverse-kinematics-for-neuro-robotic-grasping","title":"Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents","date":"2024-04-12","arxiv_id":"2404.08825","repositories_listed":1,"syntology":null},{"url":"/paper/llm-seg-bridging-image-segmentation-and-large","slug":"llm-seg-bridging-image-segmentation-and-large","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","date":"2024-04-12","arxiv_id":"2404.08767","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/llm-seg-bridging-image-segmentation-and-large#ran","syntology_url":"https://syntology.ai/paper/2404.08767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08767"}},"official":{"repos":["wangjunchi/llmseg"],"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/pre-training-small-base-lms-with-fewer-tokens","slug":"pre-training-small-base-lms-with-fewer-tokens","title":"Inheritune: Training Smaller Yet More Attentive Language Models","date":"2024-04-12","arxiv_id":"2404.08634","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":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pre-training-small-base-lms-with-fewer-tokens#ran","syntology_url":"https://syntology.ai/paper/2404.08634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08634"}},"official":{"repos":["sanyalsunny111/llm-inheritune"],"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/the-elephant-in-the-room-rethinking-the-usage","slug":"the-elephant-in-the-room-rethinking-the-usage","title":"The Elephant in the Room: Rethinking the Usage of Pre-trained Language Model in Sequential Recommendation","date":"2024-04-12","arxiv_id":"2404.08796","repositories_listed":1,"syntology":null},{"url":"/paper/behavior-trees-enable-structured-programming","slug":"behavior-trees-enable-structured-programming","title":"Behavior Trees Enable Structured Programming of Language Model Agents","date":"2024-04-11","arxiv_id":"2404.07439","repositories_listed":1,"syntology":null},{"url":"/paper/ferret-v2-an-improved-baseline-for-referring","slug":"ferret-v2-an-improved-baseline-for-referring","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","date":"2024-04-11","arxiv_id":"2404.07973","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ferret-v2-an-improved-baseline-for-referring#ran","syntology_url":"https://syntology.ai/paper/2404.07973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07973"}},"official":null}},{"url":"/paper/from-words-to-numbers-your-large-language","slug":"from-words-to-numbers-your-large-language","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","date":"2024-04-11","arxiv_id":"2404.07544","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/from-words-to-numbers-your-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.07544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07544"}},"official":{"repos":["robertvacareanu/llm4regression"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/high-dimension-human-value-representation-in","slug":"high-dimension-human-value-representation-in","title":"High-Dimension Human Value Representation in Large Language Models","date":"2024-04-11","arxiv_id":"2404.07900","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/high-dimension-human-value-representation-in#ran","syntology_url":"https://syntology.ai/paper/2404.07900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07900"}},"official":{"repos":["hltchkust/univar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/language-imbalance-can-boost-cross-lingual","slug":"language-imbalance-can-boost-cross-lingual","title":"The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments","date":"2024-04-11","arxiv_id":"2404.07982","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-imbalance-can-boost-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2404.07982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07982"}},"official":{"repos":["antonschafer/xling-imbalance"],"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/lavy-vietnamese-multimodal-large-language","slug":"lavy-vietnamese-multimodal-large-language","title":"LaVy: Vietnamese Multimodal Large Language Model","date":"2024-04-11","arxiv_id":"2404.07922","repositories_listed":1,"syntology":null},{"url":"/paper/multi-image-visual-question-answering-for","slug":"multi-image-visual-question-answering-for","title":"Language Models Meet Anomaly Detection for Better Interpretability and Generalizability","date":"2024-04-11","arxiv_id":"2404.07622","repositories_listed":1,"syntology":null},{"url":"/paper/openbias-open-set-bias-detection-in-text-to","slug":"openbias-open-set-bias-detection-in-text-to","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","date":"2024-04-11","arxiv_id":"2404.07990","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openbias-open-set-bias-detection-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2404.07990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07990"}},"official":{"repos":["picsart-ai-research/openbias"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/post-hoc-reversal-are-we-selecting-models","slug":"post-hoc-reversal-are-we-selecting-models","title":"Post-Hoc Reversal: Are We Selecting Models Prematurely?","date":"2024-04-11","arxiv_id":"2404.07815","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":1,"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/post-hoc-reversal-are-we-selecting-models#ran","syntology_url":"https://syntology.ai/paper/2404.07815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07815"}},"official":{"repos":["rishabh-ranjan/post-hoc-reversal"],"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/recurrentgemma-moving-past-transformers-for","slug":"recurrentgemma-moving-past-transformers-for","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","date":"2024-04-11","arxiv_id":"2404.07839","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/recurrentgemma-moving-past-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2404.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07839"}},"official":{"repos":["google-deepmind/recurrentgemma"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-language-model-with-generalized","slug":"scalable-language-model-with-generalized","title":"Scalable Language Model with Generalized Continual Learning","date":"2024-04-11","arxiv_id":"2404.07470","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scalable-language-model-with-generalized#ran","syntology_url":"https://syntology.ai/paper/2404.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07470"}},"official":{"repos":["pbihao/slm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/continuous-language-model-interpolation-for","slug":"continuous-language-model-interpolation-for","title":"Continuous Language Model Interpolation for Dynamic and Controllable Text Generation","date":"2024-04-10","arxiv_id":"2404.07117","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/continuous-language-model-interpolation-for#ran","syntology_url":"https://syntology.ai/paper/2404.07117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07117"}},"official":{"repos":["skangasl/continuous-lm-interpolation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-from-failure-fine-tuning-llms-with","slug":"learn-from-failure-fine-tuning-llms-with","title":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","date":"2024-04-10","arxiv_id":"2404.07382","repositories_listed":1,"syntology":null},{"url":"/paper/lossless-acceleration-of-large-language-model","slug":"lossless-acceleration-of-large-language-model","title":"Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding","date":"2024-04-10","arxiv_id":"2404.08698","repositories_listed":1,"syntology":null},{"url":"/paper/oracle-large-vision-language-models-for","slug":"oracle-large-vision-language-models-for","title":"ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling","date":"2024-04-10","arxiv_id":"2404.07031","repositories_listed":1,"syntology":null},{"url":"/paper/umbrae-unified-multimodal-decoding-of-brain","slug":"umbrae-unified-multimodal-decoding-of-brain","title":"UMBRAE: Unified Multimodal Brain Decoding","date":"2024-04-10","arxiv_id":"2404.07202","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/umbrae-unified-multimodal-decoding-of-brain#ran","syntology_url":"https://syntology.ai/paper/2404.07202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07202"}},"official":{"repos":["weihaox/UMBRAE"],"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/we-re-calling-an-intervention-taking-a-closer","slug":"we-re-calling-an-intervention-taking-a-closer","title":"We're Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text","date":"2024-04-10","arxiv_id":"2404.07304","repositories_listed":1,"syntology":null},{"url":"/paper/does-transformer-interpretability-transfer-to","slug":"does-transformer-interpretability-transfer-to","title":"Does Transformer Interpretability Transfer to RNNs?","date":"2024-04-09","arxiv_id":"2404.05971","repositories_listed":1,"syntology":null},{"url":"/paper/elephants-never-forget-memorization-and","slug":"elephants-never-forget-memorization-and","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","date":"2024-04-09","arxiv_id":"2404.06209","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elephants-never-forget-memorization-and#ran","syntology_url":"https://syntology.ai/paper/2404.06209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06209"}},"official":{"repos":["interpretml/llm-tabular-memorization-checker"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-decision-analysis-with-a-large","slug":"enhancing-decision-analysis-with-a-large","title":"Enhancing Decision Analysis with a Large Language Model: pyDecision a Comprehensive Library of MCDA Methods in Python","date":"2024-04-09","arxiv_id":"2404.06370","repositories_listed":1,"syntology":null},{"url":"/paper/freeeval-a-modular-framework-for-trustworthy","slug":"freeeval-a-modular-framework-for-trustworthy","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","date":"2024-04-09","arxiv_id":"2404.06003","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/freeeval-a-modular-framework-for-trustworthy#ran","syntology_url":"https://syntology.ai/paper/2404.06003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06003"}},"official":{"repos":["wisdomshell/freeeval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-effect-of-near-duplicate-subwords-in","slug":"on-the-effect-of-near-duplicate-subwords-in","title":"On the Effect of (Near) Duplicate Subwords in Language Modelling","date":"2024-04-09","arxiv_id":"2404.06508","repositories_listed":1,"syntology":null},{"url":"/paper/optimization-methods-for-personalizing-large","slug":"optimization-methods-for-personalizing-large","title":"Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation","date":"2024-04-09","arxiv_id":"2404.05970","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimization-methods-for-personalizing-large#ran","syntology_url":"https://syntology.ai/paper/2404.05970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05970"}},"official":{"repos":["lamp-benchmark/lamp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/take-a-look-at-it-rethinking-how-to-evaluate","slug":"take-a-look-at-it-rethinking-how-to-evaluate","title":"Rethinking How to Evaluate Language Model Jailbreak","date":"2024-04-09","arxiv_id":"2404.06407","repositories_listed":1,"syntology":null},{"url":"/paper/text-based-reasoning-about-vector-graphics","slug":"text-based-reasoning-about-vector-graphics","title":"Visually Descriptive Language Model for Vector Graphics Reasoning","date":"2024-04-09","arxiv_id":"2404.06479","repositories_listed":1,"syntology":null},{"url":"/paper/360degrea-towards-a-reusable-experience","slug":"360degrea-towards-a-reusable-experience","title":"360$^\\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System","date":"2024-04-08","arxiv_id":"2404.05569","repositories_listed":1,"syntology":null},{"url":"/paper/chinese-sequence-labeling-with-semi","slug":"chinese-sequence-labeling-with-semi","title":"Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training","date":"2024-04-08","arxiv_id":"2404.05560","repositories_listed":1,"syntology":null},{"url":"/paper/have-you-merged-my-model-on-the-robustness-of","slug":"have-you-merged-my-model-on-the-robustness-of","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","date":"2024-04-08","arxiv_id":"2404.05188","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/have-you-merged-my-model-on-the-robustness-of#ran","syntology_url":"https://syntology.ai/paper/2404.05188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05188"}},"official":{"repos":["thuccslab/mergeguard"],"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/moma-multimodal-llm-adapter-for-fast","slug":"moma-multimodal-llm-adapter-for-fast","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","date":"2024-04-08","arxiv_id":"2404.05674","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/moma-multimodal-llm-adapter-for-fast#ran","syntology_url":"https://syntology.ai/paper/2404.05674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05674"}},"official":{"repos":["bytedance/MoMA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/promptad-learning-prompts-with-only-normal","slug":"promptad-learning-prompts-with-only-normal","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","date":"2024-04-08","arxiv_id":"2404.05231","repositories_listed":1,"syntology":{"n":16,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/promptad-learning-prompts-with-only-normal#ran","syntology_url":"https://syntology.ai/paper/2404.05231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05231"}},"official":{"repos":["funz-0/promptad"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-augmented-open-vocabulary-object","slug":"retrieval-augmented-open-vocabulary-object","title":"Retrieval-Augmented Open-Vocabulary Object Detection","date":"2024-04-08","arxiv_id":"2404.05687","repositories_listed":1,"syntology":null},{"url":"/paper/safetyprompts-a-systematic-review-of-open","slug":"safetyprompts-a-systematic-review-of-open","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","date":"2024-04-08","arxiv_id":"2404.05399","repositories_listed":1,"syntology":null},{"url":"/paper/speechalign-aligning-speech-generation-to","slug":"speechalign-aligning-speech-generation-to","title":"SpeechAlign: Aligning Speech Generation to Human Preferences","date":"2024-04-08","arxiv_id":"2404.05600","repositories_listed":1,"syntology":null},{"url":"/paper/test-time-zero-shot-temporal-action","slug":"test-time-zero-shot-temporal-action","title":"Test-Time Zero-Shot Temporal Action Localization","date":"2024-04-08","arxiv_id":"2404.05426","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/test-time-zero-shot-temporal-action#ran","syntology_url":"https://syntology.ai/paper/2404.05426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05426"}},"official":{"repos":["benedettaliberatori/t3al"],"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/vietmed-a-dataset-and-benchmark-for-automatic","slug":"vietmed-a-dataset-and-benchmark-for-automatic","title":"VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain","date":"2024-04-08","arxiv_id":"2404.05659","repositories_listed":1,"syntology":null},{"url":"/paper/xiwu-a-basis-flexible-and-learnable-llm-for","slug":"xiwu-a-basis-flexible-and-learnable-llm-for","title":"Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics","date":"2024-04-08","arxiv_id":"2404.08001","repositories_listed":1,"syntology":null},{"url":"/paper/pairaug-what-can-augmented-image-text-pairs","slug":"pairaug-what-can-augmented-image-text-pairs","title":"PairAug: What Can Augmented Image-Text Pairs Do for Radiology?","date":"2024-04-07","arxiv_id":"2404.04960","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pairaug-what-can-augmented-image-text-pairs#ran","syntology_url":"https://syntology.ai/paper/2404.04960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04960"}},"official":{"repos":["ytongxie/pairaug"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/squeezeattention-2d-management-of-kv-cache-in","slug":"squeezeattention-2d-management-of-kv-cache-in","title":"SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget","date":"2024-04-07","arxiv_id":"2404.04793","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/squeezeattention-2d-management-of-kv-cache-in#ran","syntology_url":"https://syntology.ai/paper/2404.04793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04793"}},"official":{"repos":["hetailang/squeezeattention"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comparison-of-methods-for-evaluating","slug":"a-comparison-of-methods-for-evaluating","title":"A Comparison of Methods for Evaluating Generative IR","date":"2024-04-05","arxiv_id":"2404.04044","repositories_listed":1,"syntology":null},{"url":"/paper/bear-a-unified-framework-for-evaluating","slug":"bear-a-unified-framework-for-evaluating","title":"BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models","date":"2024-04-05","arxiv_id":"2404.04113","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/bear-a-unified-framework-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2404.04113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04113"}},"official":{"repos":["lm-pub-quiz/lm-pub-quiz"],"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/dwell-in-the-beginning-how-language-models","slug":"dwell-in-the-beginning-how-language-models","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","date":"2024-04-05","arxiv_id":"2404.04163","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":10,"phrase":"10 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dwell-in-the-beginning-how-language-models#ran","syntology_url":"https://syntology.ai/paper/2404.04163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04163"}},"official":{"repos":["cxcscmu/longembeddinganalysis"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/forget-nli-use-a-dictionary-zero-shot-topic","slug":"forget-nli-use-a-dictionary-zero-shot-topic","title":"Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish","date":"2024-04-05","arxiv_id":"2404.03912","repositories_listed":1,"syntology":null},{"url":"/paper/image-text-co-decomposition-for-text","slug":"image-text-co-decomposition-for-text","title":"Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation","date":"2024-04-05","arxiv_id":"2404.04231","repositories_listed":1,"syntology":null},{"url":"/paper/physics-event-classification-using-large","slug":"physics-event-classification-using-large","title":"Physics Event Classification Using Large Language Models","date":"2024-04-05","arxiv_id":"2404.05752","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":3,"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/physics-event-classification-using-large#ran","syntology_url":"https://syntology.ai/paper/2404.05752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05752"}},"official":{"repos":["ai4eic/ai4eichackathon2023-streamlit"],"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/autowebglm-bootstrap-and-reinforce-a-large","slug":"autowebglm-bootstrap-and-reinforce-a-large","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","date":"2024-04-04","arxiv_id":"2404.03648","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/autowebglm-bootstrap-and-reinforce-a-large#ran","syntology_url":"https://syntology.ai/paper/2404.03648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03648"}},"official":{"repos":["thudm/autowebglm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cbr-rag-case-based-reasoning-for-retrieval","slug":"cbr-rag-case-based-reasoning-for-retrieval","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","date":"2024-04-04","arxiv_id":"2404.04302","repositories_listed":1,"syntology":null},{"url":"/paper/conflare-conformal-large-language-model","slug":"conflare-conformal-large-language-model","title":"CONFLARE: CONFormal LArge language model REtrieval","date":"2024-04-04","arxiv_id":"2404.04287","repositories_listed":1,"syntology":null},{"url":"/paper/edisum-summarizing-and-explaining-wikipedia","slug":"edisum-summarizing-and-explaining-wikipedia","title":"Edisum: Summarizing and Explaining Wikipedia Edits at Scale","date":"2024-04-04","arxiv_id":"2404.03428","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-evolution-an-iterated-learning","slug":"language-model-evolution-an-iterated-learning","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","date":"2024-04-04","arxiv_id":"2404.04286","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-model-evolution-an-iterated-learning#ran","syntology_url":"https://syntology.ai/paper/2404.04286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04286"}},"official":{"repos":["joshua-ren/iicl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-the-impact-of-outlier-channels-for","slug":"mitigating-the-impact-of-outlier-channels-for","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","date":"2024-04-04","arxiv_id":"2404.03605","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-language-modeling-paradigm","slug":"understanding-language-modeling-paradigm","title":"Understanding Language Modeling Paradigm Adaptations in Recommender Systems: Lessons Learned and Open Challenges","date":"2024-04-04","arxiv_id":"2404.03788","repositories_listed":1,"syntology":null},{"url":"/paper/affective-nli-towards-accurate-and","slug":"affective-nli-towards-accurate-and","title":"Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation","date":"2024-04-03","arxiv_id":"2404.02589","repositories_listed":1,"syntology":null},{"url":"/paper/angofa-leveraging-ofa-embedding","slug":"angofa-leveraging-ofa-embedding","title":"ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model","date":"2024-04-03","arxiv_id":"2404.02534","repositories_listed":1,"syntology":null},{"url":"/paper/fpt-feature-prompt-tuning-for-few-shot","slug":"fpt-feature-prompt-tuning-for-few-shot","title":"FPT: Feature Prompt Tuning for Few-shot Readability Assessment","date":"2024-04-03","arxiv_id":"2404.02772","repositories_listed":1,"syntology":null},{"url":"/paper/lvlm-intrepret-an-interpretability-tool-for","slug":"lvlm-intrepret-an-interpretability-tool-for","title":"LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models","date":"2024-04-03","arxiv_id":"2404.03118","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lvlm-intrepret-an-interpretability-tool-for#ran","syntology_url":"https://syntology.ai/paper/2404.03118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03118"}},"official":{"repos":["IntelLabs/lvlm-interpret"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-large-language-model-based-game","slug":"a-survey-on-large-language-model-based-game","title":"A Survey on Large Language Model-Based Game Agents","date":"2024-04-02","arxiv_id":"2404.02039","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-automated-distractor-generation-for","slug":"exploring-automated-distractor-generation-for","title":"Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models","date":"2024-04-02","arxiv_id":"2404.02124","repositories_listed":1,"syntology":null},{"url":"/paper/flawn-t5-an-empirical-examination-of","slug":"flawn-t5-an-empirical-examination-of","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","date":"2024-04-02","arxiv_id":"2404.02127","repositories_listed":1,"syntology":null},{"url":"/paper/improving-retrieval-augmented-open-domain","slug":"improving-retrieval-augmented-open-domain","title":"Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts","date":"2024-04-02","arxiv_id":"2404.02022","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-guided-interpretable-video","slug":"language-model-guided-interpretable-video","title":"Language Model Guided Interpretable Video Action Reasoning","date":"2024-04-02","arxiv_id":"2404.01591","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-orchestrating","slug":"large-language-models-for-orchestrating","title":"Large Language Models for Orchestrating Bimanual Robots","date":"2024-04-02","arxiv_id":"2404.02018","repositories_listed":1,"syntology":null},{"url":"/paper/laying-anchors-semantically-priming-numerals","slug":"laying-anchors-semantically-priming-numerals","title":"Laying Anchors: Semantically Priming Numerals in Language Modeling","date":"2024-04-02","arxiv_id":"2404.01536","repositories_listed":1,"syntology":null},{"url":"/paper/llms-in-the-loop-leveraging-large-language","slug":"llms-in-the-loop-leveraging-large-language","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","date":"2024-04-02","arxiv_id":"2404.02261","repositories_listed":1,"syntology":null},{"url":"/paper/m2sa-multimodal-and-multilingual-model-for","slug":"m2sa-multimodal-and-multilingual-model-for","title":"M2SA: Multimodal and Multilingual Model for Sentiment Analysis of Tweets","date":"2024-04-02","arxiv_id":"2404.01753","repositories_listed":1,"syntology":null},{"url":"/paper/motionchain-conversational-motion-controllers","slug":"motionchain-conversational-motion-controllers","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts","date":"2024-04-02","arxiv_id":"2404.01700","repositories_listed":1,"syntology":null},{"url":"/paper/self-organized-agents-a-llm-multi-agent","slug":"self-organized-agents-a-llm-multi-agent","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","date":"2024-04-02","arxiv_id":"2404.02183","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-organized-agents-a-llm-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2404.02183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02183"}},"official":{"repos":["tsukushiai/self-organized-agent"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sentence-level-media-bias-analysis-with-event","slug":"sentence-level-media-bias-analysis-with-event","title":"Sentence-level Media Bias Analysis with Event Relation Graph","date":"2024-04-02","arxiv_id":"2404.01722","repositories_listed":1,"syntology":null},{"url":"/paper/aragog-advanced-rag-output-grading","slug":"aragog-advanced-rag-output-grading","title":"ARAGOG: Advanced RAG Output Grading","date":"2024-04-01","arxiv_id":"2404.01037","repositories_listed":1,"syntology":null},{"url":"/paper/developing-safe-and-responsible-large","slug":"developing-safe-and-responsible-large","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","date":"2024-04-01","arxiv_id":"2404.01399","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":2,"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/developing-safe-and-responsible-large#ran","syntology_url":"https://syntology.ai/paper/2404.01399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01399"}},"official":{"repos":["shainarazavi/safe-responsible-llm"],"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/direct-preference-optimization-of-video-large","slug":"direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","arxiv_id":"2404.01258","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-optimization-of-video-large#ran","syntology_url":"https://syntology.ai/paper/2404.01258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01258"}},"official":{"repos":["riflezhang/llava-hound-dpo"],"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/do-language-models-plan-ahead-for-future","slug":"do-language-models-plan-ahead-for-future","title":"Do language models plan ahead for future tokens?","date":"2024-04-01","arxiv_id":"2404.00859","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/do-language-models-plan-ahead-for-future#ran","syntology_url":"https://syntology.ai/paper/2404.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00859"}},"official":{"repos":["wiwu2390/futuregpt2-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/evalverse-unified-and-accessible-library-for","slug":"evalverse-unified-and-accessible-library-for","title":"Evalverse: Unified and Accessible Library for Large Language Model Evaluation","date":"2024-04-01","arxiv_id":"2404.00943","repositories_listed":1,"syntology":null},{"url":"/paper/learning-by-correction-efficient-tuning-task","slug":"learning-by-correction-efficient-tuning-task","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","date":"2024-04-01","arxiv_id":"2404.00909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-correction-efficient-tuning-task#ran","syntology_url":"https://syntology.ai/paper/2404.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00909"}},"official":{"repos":["shtuplus/iccc_cvpr2024"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lipsum-ft-robust-fine-tuning-of-zero-shot","slug":"lipsum-ft-robust-fine-tuning-of-zero-shot","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","date":"2024-04-01","arxiv_id":"2404.00860","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lipsum-ft-robust-fine-tuning-of-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2404.00860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00860"}},"official":{"repos":["cs-giung/lipsum-ft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lite-modeling-environmental-ecosystems-with","slug":"lite-modeling-environmental-ecosystems-with","title":"LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models","date":"2024-04-01","arxiv_id":"2404.01165","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/lite-modeling-environmental-ecosystems-with#ran","syntology_url":"https://syntology.ai/paper/2404.01165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01165"}},"official":{"repos":["hrlics/lite"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/query-performance-prediction-using-relevance","slug":"query-performance-prediction-using-relevance","title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","date":"2024-04-01","arxiv_id":"2404.01012","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/query-performance-prediction-using-relevance#ran","syntology_url":"https://syntology.ai/paper/2404.01012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01012"}},"official":{"repos":["chuanmeng/qpp-genre"],"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/regularized-best-of-n-sampling-to-mitigate","slug":"regularized-best-of-n-sampling-to-mitigate","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","date":"2024-04-01","arxiv_id":"2404.01054","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/regularized-best-of-n-sampling-to-mitigate#ran","syntology_url":"https://syntology.ai/paper/2404.01054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01054"}},"official":{"repos":["CyberAgentAILab/regularized-bon"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/stream-of-search-sos-learning-to-search-in","slug":"stream-of-search-sos-learning-to-search-in","title":"Stream of Search (SoS): Learning to Search in Language","date":"2024-04-01","arxiv_id":"2404.03683","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":3,"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/stream-of-search-sos-learning-to-search-in#ran","syntology_url":"https://syntology.ai/paper/2404.03683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03683"}},"official":{"repos":["kanishkg/stream-of-search"],"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/a-controlled-reevaluation-of-coreference","slug":"a-controlled-reevaluation-of-coreference","title":"A Controlled Reevaluation of Coreference Resolution Models","date":"2024-03-31","arxiv_id":"2404.00727","repositories_listed":1,"syntology":null},{"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/humane-speech-synthesis-through-zero-shot","slug":"humane-speech-synthesis-through-zero-shot","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation","date":"2024-03-31","arxiv_id":"2404.01339","repositories_listed":1,"syntology":null}],"record_sha256":"aa2af73d17690c7e681b0ac807a68af3ae3967e3ca0c7dcf98a40ec27ed8c01e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}