{"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/text-generation/papers/9","list_of":"/task/text-generation","task":"Text Generation","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":9,"pages_in_order":54,"rows_per_page":100,"rows":[801,900],"of":5335,"counts":{"archive_papers_tagged":5335,"with_a_code_link":2047,"where_syntology_ran_a_sample":610,"not_listed_spam_title":0,"listed":5335,"listed_where_code_ran":610,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":503,"every_run_a_failure_of_syntologys_instrument":107,"listed_with_a_run_with_no_instrument_failure":503,"listed_every_run_a_failure_of_syntologys_instrument":107,"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/text-generation","prev":"/task/text-generation/papers/8","next":"/task/text-generation/papers/10","papers":[{"url":"/paper/towards-llm-recsys-alignment-with-textual-id","slug":"towards-llm-recsys-alignment-with-textual-id","title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","date":"2024-03-27","arxiv_id":"2403.19021","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"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) · 0 unverified","sample_list":"/paper/towards-llm-recsys-alignment-with-textual-id#ran","syntology_url":"https://syntology.ai/paper/2403.19021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19021"}},"official":{"repos":["agiresearch/idgenrec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/illuminer-instruction-tuned-large-language","slug":"illuminer-instruction-tuned-large-language","title":"ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler","date":"2024-03-26","arxiv_id":"2403.17536","repositories_listed":1,"syntology":null},{"url":"/paper/attribute-first-then-generate-locally","slug":"attribute-first-then-generate-locally","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","date":"2024-03-25","arxiv_id":"2403.17104","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/attribute-first-then-generate-locally#ran","syntology_url":"https://syntology.ai/paper/2403.17104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17104"}},"official":{"repos":["lovodkin93/attribute-first-then-generate"],"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/toxcl-a-unified-framework-for-toxic-speech","slug":"toxcl-a-unified-framework-for-toxic-speech","title":"ToXCL: A Unified Framework for Toxic Speech Detection and Explanation","date":"2024-03-25","arxiv_id":"2403.16685","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-reward-adjustment-in-multi-reward","slug":"dynamic-reward-adjustment-in-multi-reward","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","date":"2024-03-20","arxiv_id":"2403.13578","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":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) · 1 unverified","sample_list":"/paper/dynamic-reward-adjustment-in-multi-reward#ran","syntology_url":"https://syntology.ai/paper/2403.13578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13578"}},"official":{"repos":["michigannlp/dynaopt"],"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/reinforcement-learning-with-token-level","slug":"reinforcement-learning-with-token-level","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","date":"2024-03-18","arxiv_id":"2403.11558","repositories_listed":1,"syntology":null},{"url":"/paper/convsdg-session-data-generation-for","slug":"convsdg-session-data-generation-for","title":"ConvSDG: Session Data Generation for Conversational Search","date":"2024-03-17","arxiv_id":"2403.11335","repositories_listed":1,"syntology":null},{"url":"/paper/dragin-dynamic-retrieval-augmented-generation","slug":"dragin-dynamic-retrieval-augmented-generation","title":"DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models","date":"2024-03-15","arxiv_id":"2403.10081","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/dragin-dynamic-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2403.10081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10081"}},"official":{"repos":["oneal2000/dragin"],"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/whose-side-are-you-on-investigating-the","slug":"whose-side-are-you-on-investigating-the","title":"Whose Side Are You On? Investigating the Political Stance of Large Language Models","date":"2024-03-15","arxiv_id":"2403.13840","repositories_listed":1,"syntology":null},{"url":"/paper/keyformer-kv-cache-reduction-through-key","slug":"keyformer-kv-cache-reduction-through-key","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","date":"2024-03-14","arxiv_id":"2403.09054","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":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) · 5 unverified","sample_list":"/paper/keyformer-kv-cache-reduction-through-key#ran","syntology_url":"https://syntology.ai/paper/2403.09054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09054"}},"official":{"repos":["d-matrix-ai/keyformer-llm"],"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/complex-reasoning-over-logical-queries-on","slug":"complex-reasoning-over-logical-queries-on","title":"Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs","date":"2024-03-12","arxiv_id":"2403.07398","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/complex-reasoning-over-logical-queries-on#ran","syntology_url":"https://syntology.ai/paper/2403.07398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07398"}},"official":{"repos":["tqfang/complex-commonsense-reasoning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/duwak-dual-watermarks-in-large-language","slug":"duwak-dual-watermarks-in-large-language","title":"Duwak: Dual Watermarks in Large Language Models","date":"2024-03-12","arxiv_id":"2403.13000","repositories_listed":1,"syntology":null},{"url":"/paper/textual-knowledge-matters-cross-modality-co","slug":"textual-knowledge-matters-cross-modality-co","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","date":"2024-03-12","arxiv_id":"2403.07369","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/textual-knowledge-matters-cross-modality-co#ran","syntology_url":"https://syntology.ai/paper/2403.07369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07369"}},"official":{"repos":["haiyangzheng/textgcd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/truth-aware-context-selection-mitigating-the","slug":"truth-aware-context-selection-mitigating-the","title":"Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts","date":"2024-03-12","arxiv_id":"2403.07556","repositories_listed":1,"syntology":null},{"url":"/paper/alarm-align-language-models-via-hierarchical","slug":"alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","arxiv_id":"2403.06754","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 7 unverified","sample_list":"/paper/alarm-align-language-models-via-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2403.06754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06754"}},"official":{"repos":["halfrot/ALaRM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/calibrating-large-language-models-using-their","slug":"calibrating-large-language-models-using-their","title":"Calibrating Large Language Models Using Their Generations Only","date":"2024-03-09","arxiv_id":"2403.05973","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/calibrating-large-language-models-using-their#ran","syntology_url":"https://syntology.ai/paper/2403.05973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05973"}},"official":{"repos":["parameterlab/apricot"],"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/enhancing-court-view-generation-with","slug":"enhancing-court-view-generation-with","title":"Enhancing Court View Generation with Knowledge Injection and Guidance","date":"2024-03-07","arxiv_id":"2403.04366","repositories_listed":1,"syntology":null},{"url":"/paper/qaq-quality-adaptive-quantization-for-llm-kv","slug":"qaq-quality-adaptive-quantization-for-llm-kv","title":"QAQ: Quality Adaptive Quantization for LLM KV Cache","date":"2024-03-07","arxiv_id":"2403.04643","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-contamination-in-evaluating-code","slug":"quantifying-contamination-in-evaluating-code","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","date":"2024-03-06","arxiv_id":"2403.04811","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quantifying-contamination-in-evaluating-code#ran","syntology_url":"https://syntology.ai/paper/2403.04811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04811"}},"official":{"repos":["yale-nlp/code-llm-contamination"],"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/routeexplainer-an-explanation-framework-for","slug":"routeexplainer-an-explanation-framework-for","title":"RouteExplainer: An Explanation Framework for Vehicle Routing Problem","date":"2024-03-06","arxiv_id":"2403.03585","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-naive-approaches-to-tell-apart-llms","slug":"exploring-naive-approaches-to-tell-apart-llms","title":"Exploring Naive Approaches to Tell Apart LLMs Productions from Human-written Text","date":"2024-03-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-knowledge-distillation","slug":"differentially-private-knowledge-distillation","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","date":"2024-03-01","arxiv_id":"2403.00932","repositories_listed":1,"syntology":null},{"url":"/paper/tencdm-understanding-the-properties-of","slug":"tencdm-understanding-the-properties-of","title":"TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings","date":"2024-02-29","arxiv_id":"2402.19097","repositories_listed":1,"syntology":null},{"url":"/paper/the-all-seeing-project-v2-towards-general","slug":"the-all-seeing-project-v2-towards-general","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","date":"2024-02-29","arxiv_id":"2402.19474","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-all-seeing-project-v2-towards-general#ran","syntology_url":"https://syntology.ai/paper/2402.19474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19474"}},"official":{"repos":["opengvlab/all-seeing"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-multi-document-information","slug":"exploring-multi-document-information","title":"A Sentiment Consolidation Framework for Meta-Review Generation","date":"2024-02-28","arxiv_id":"2402.18005","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/exploring-multi-document-information#ran","syntology_url":"https://syntology.ai/paper/2402.18005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18005"}},"official":{"repos":["oaimli/metareviewinglogic"],"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/grounding-language-models-for-visual-entity","slug":"grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","arxiv_id":"2402.18695","repositories_listed":1,"syntology":{"n":26,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/grounding-language-models-for-visual-entity#ran","syntology_url":"https://syntology.ai/paper/2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"official":{"repos":["mrzilinxiao/autover"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-open-ended-text-generation-via","slug":"improving-open-ended-text-generation-via","title":"Improving Open-Ended Text Generation via Adaptive Decoding","date":"2024-02-28","arxiv_id":"2402.18223","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improving-open-ended-text-generation-via#ran","syntology_url":"https://syntology.ai/paper/2402.18223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18223"}},"official":{"repos":["zwhong714/adaptive_decoding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ambignlg-addressing-task-ambiguity-in","slug":"ambignlg-addressing-task-ambiguity-in","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","date":"2024-02-27","arxiv_id":"2402.17717","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-is-accurate-generation","slug":"retrieval-is-accurate-generation","title":"Retrieval is Accurate Generation","date":"2024-02-27","arxiv_id":"2402.17532","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-is-accurate-generation#ran","syntology_url":"https://syntology.ai/paper/2402.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17532"}},"official":{"repos":["gmftbygmftby/copyisallyouneed"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","unlocated"]}}},{"url":"/paper/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/asem-enhancing-empathy-in-chatbot-through","slug":"asem-enhancing-empathy-in-chatbot-through","title":"ASEM: Enhancing Empathy in Chatbot through Attention-based Sentiment and Emotion Modeling","date":"2024-02-25","arxiv_id":"2402.16194","repositories_listed":1,"syntology":null},{"url":"/paper/chatmusician-understanding-and-generating","slug":"chatmusician-understanding-and-generating","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","date":"2024-02-25","arxiv_id":"2402.16153","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/chatmusician-understanding-and-generating#ran","syntology_url":"https://syntology.ai/paper/2402.16153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16153"}},"official":{"repos":["hf-lin/ChatMusician"],"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/likelihood-based-mitigation-of-evaluation","slug":"likelihood-based-mitigation-of-evaluation","title":"Likelihood-based Mitigation of Evaluation Bias in Large Language Models","date":"2024-02-25","arxiv_id":"2402.15987","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/likelihood-based-mitigation-of-evaluation#ran","syntology_url":"https://syntology.ai/paper/2402.15987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15987"}},"official":{"repos":["stjohn2007/likelihood_bias"],"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/counterfactual-generation-with-1","slug":"counterfactual-generation-with-1","title":"Counterfactual Generation with Identifiability Guarantees","date":"2024-02-23","arxiv_id":"2402.15309","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":4,"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/counterfactual-generation-with-1#ran","syntology_url":"https://syntology.ai/paper/2402.15309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15309"}},"official":{"repos":["hanqi-qi/matte"],"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/fine-grained-detoxification-via-instance","slug":"fine-grained-detoxification-via-instance","title":"Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models","date":"2024-02-23","arxiv_id":"2402.15202","repositories_listed":1,"syntology":null},{"url":"/paper/cev-lm-controlled-edit-vector-language-model","slug":"cev-lm-controlled-edit-vector-language-model","title":"CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations","date":"2024-02-22","arxiv_id":"2402.14290","repositories_listed":1,"syntology":null},{"url":"/paper/generalizing-reward-modeling-for-out-of","slug":"generalizing-reward-modeling-for-out-of","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","date":"2024-02-22","arxiv_id":"2402.14760","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-concept","slug":"leveraging-large-language-models-for-concept","title":"Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education","date":"2024-02-22","arxiv_id":"2402.14293","repositories_listed":1,"syntology":null},{"url":"/paper/my-answer-is-c-first-token-probabilities-do","slug":"my-answer-is-c-first-token-probabilities-do","title":"\"My Answer is C\": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models","date":"2024-02-22","arxiv_id":"2402.14499","repositories_listed":1,"syntology":null},{"url":"/paper/ufo-a-unified-and-flexible-framework-for","slug":"ufo-a-unified-and-flexible-framework-for","title":"UFO: a Unified and Flexible Framework for Evaluating Factuality of Large Language Models","date":"2024-02-22","arxiv_id":"2402.14690","repositories_listed":1,"syntology":null},{"url":"/paper/a-multimodal-in-context-tuning-approach-for-e","slug":"a-multimodal-in-context-tuning-approach-for-e","title":"A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation","date":"2024-02-21","arxiv_id":"2402.13587","repositories_listed":1,"syntology":null},{"url":"/paper/ouroboros-speculative-decoding-with-large","slug":"ouroboros-speculative-decoding-with-large","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","date":"2024-02-21","arxiv_id":"2402.13720","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ouroboros-speculative-decoding-with-large#ran","syntology_url":"https://syntology.ai/paper/2402.13720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13720"}},"official":{"repos":["thunlp/ouroboros"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-but-effective-approach-to-improve-1","slug":"a-simple-but-effective-approach-to-improve-1","title":"A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction","date":"2024-02-20","arxiv_id":"2402.13364","repositories_listed":1,"syntology":null},{"url":"/paper/a-touch-vision-and-language-dataset-for","slug":"a-touch-vision-and-language-dataset-for","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","date":"2024-02-20","arxiv_id":"2402.13232","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/a-touch-vision-and-language-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2402.13232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13232"}},"official":{"repos":["Max-Fu/tvl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-user-friendly-framework-for-generating","slug":"a-user-friendly-framework-for-generating","title":"A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis","date":"2024-02-20","arxiv_id":"2402.12760","repositories_listed":1,"syntology":null},{"url":"/paper/countercurate-enhancing-physical-and-semantic","slug":"countercurate-enhancing-physical-and-semantic","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","date":"2024-02-20","arxiv_id":"2402.13254","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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) · 0 unverified","sample_list":"/paper/countercurate-enhancing-physical-and-semantic#ran","syntology_url":"https://syntology.ai/paper/2402.13254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13254"}},"official":{"repos":["hansolo9682/countercurate"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/owsm-ctc-an-open-encoder-only-speech","slug":"owsm-ctc-an-open-encoder-only-speech","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","date":"2024-02-20","arxiv_id":"2402.12654","repositories_listed":1,"syntology":null},{"url":"/paper/high-quality-data-to-text-generation-for","slug":"high-quality-data-to-text-generation-for","title":"High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models","date":"2024-02-19","arxiv_id":"2402.12267","repositories_listed":1,"syntology":null},{"url":"/paper/hu-at-semeval-2024-task-8a-can-contrastive","slug":"hu-at-semeval-2024-task-8a-can-contrastive","title":"HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?","date":"2024-02-19","arxiv_id":"2402.11815","repositories_listed":1,"syntology":null},{"url":"/paper/standardize-aligning-language-models-with","slug":"standardize-aligning-language-models-with","title":"Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation","date":"2024-02-19","arxiv_id":"2402.12593","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-failure-integrating-negative","slug":"learning-from-failure-integrating-negative","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","date":"2024-02-18","arxiv_id":"2402.11651","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-from-failure-integrating-negative#ran","syntology_url":"https://syntology.ai/paper/2402.11651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11651"}},"official":{"repos":["reason-wang/nat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/perils-of-self-feedback-self-bias-amplifies","slug":"perils-of-self-feedback-self-bias-amplifies","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","date":"2024-02-18","arxiv_id":"2402.11436","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/perils-of-self-feedback-self-bias-amplifies#ran","syntology_url":"https://syntology.ai/paper/2402.11436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11436"}},"official":{"repos":["xu1998hz/llm_self_bias"],"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/controlled-text-generation-for-large-language","slug":"controlled-text-generation-for-large-language","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","date":"2024-02-17","arxiv_id":"2402.11218","repositories_listed":1,"syntology":null},{"url":"/paper/panda-pedantic-answer-correctness","slug":"panda-pedantic-answer-correctness","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","date":"2024-02-17","arxiv_id":"2402.11161","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-precision-and-recall-to-assess-the","slug":"exploring-precision-and-recall-to-assess-the","title":"Exploring Precision and Recall to assess the quality and diversity of LLMs","date":"2024-02-16","arxiv_id":"2402.10693","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/exploring-precision-and-recall-to-assess-the#ran","syntology_url":"https://syntology.ai/paper/2402.10693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10693"}},"official":{"repos":["alexverine/pr-4-llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-structure-measuring-introducing-pdd","slug":"unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-evaluation-of-model-editing","slug":"long-form-evaluation-of-model-editing","title":"Long-form evaluation of model editing","date":"2024-02-14","arxiv_id":"2402.09394","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":0,"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/long-form-evaluation-of-model-editing#ran","syntology_url":"https://syntology.ai/paper/2402.09394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09394"}},"official":{"repos":["domenicrosati/longform-evaluation-model-editing"],"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/syntaxshap-syntax-aware-explainability-method","slug":"syntaxshap-syntax-aware-explainability-method","title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","date":"2024-02-14","arxiv_id":"2402.09259","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/syntaxshap-syntax-aware-explainability-method#ran","syntology_url":"https://syntology.ai/paper/2402.09259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09259"}},"official":{"repos":["k-amara/syntax-shap"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/cold-attack-jailbreaking-llms-with","slug":"cold-attack-jailbreaking-llms-with","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","date":"2024-02-13","arxiv_id":"2402.08679","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 4 unverified","sample_list":"/paper/cold-attack-jailbreaking-llms-with#ran","syntology_url":"https://syntology.ai/paper/2402.08679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08679"}},"official":{"repos":["yu-fangxu/cold-attack"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"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/synthesizing-sentiment-controlled-feedback","slug":"synthesizing-sentiment-controlled-feedback","title":"Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data","date":"2024-02-12","arxiv_id":"2402.07640","repositories_listed":1,"syntology":null},{"url":"/paper/instruct-once-chat-consistently-in-multiple","slug":"instruct-once-chat-consistently-in-multiple","title":"Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue","date":"2024-02-10","arxiv_id":"2402.06967","repositories_listed":1,"syntology":null},{"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/is-it-possible-to-edit-large-language-models","slug":"is-it-possible-to-edit-large-language-models","title":"On the Robustness of Editing Large Language Models","date":"2024-02-08","arxiv_id":"2402.05827","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"11 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/is-it-possible-to-edit-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05827"}},"official":{"repos":["xbmxb/edit_analysis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/personalized-text-generation-with-fine","slug":"personalized-text-generation-with-fine","title":"Personalized Text Generation with Fine-Grained Linguistic Control","date":"2024-02-07","arxiv_id":"2402.04914","repositories_listed":1,"syntology":null},{"url":"/paper/transllama-llm-based-simultaneous-translation","slug":"transllama-llm-based-simultaneous-translation","title":"TransLLaMa: LLM-based Simultaneous Translation System","date":"2024-02-07","arxiv_id":"2402.04636","repositories_listed":1,"syntology":null},{"url":"/paper/shadowcast-stealthy-data-poisoning-attacks","slug":"shadowcast-stealthy-data-poisoning-attacks","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","date":"2024-02-05","arxiv_id":"2402.06659","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shadowcast-stealthy-data-poisoning-attacks#ran","syntology_url":"https://syntology.ai/paper/2402.06659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06659"}},"official":{"repos":["umd-huang-lab/vlm-poisoning"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comparative-analysis-of-conversational","slug":"a-comparative-analysis-of-conversational","title":"A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation","date":"2024-02-02","arxiv_id":"2402.01495","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/hidding-the-ghostwriters-an-adversarial","slug":"hidding-the-ghostwriters-an-adversarial","title":"Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay Detection","date":"2024-02-01","arxiv_id":"2402.00412","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/reagent-towards-a-model-agnostic-feature","slug":"reagent-towards-a-model-agnostic-feature","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","date":"2024-02-01","arxiv_id":"2402.00794","repositories_listed":1,"syntology":null},{"url":"/paper/locost-state-space-models-for-long-document","slug":"locost-state-space-models-for-long-document","title":"LOCOST: State-Space Models for Long Document Abstractive Summarization","date":"2024-01-31","arxiv_id":"2401.17919","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-clinical-pseudo-notes-for","slug":"multimodal-clinical-pseudo-notes-for","title":"Emergency Department Decision Support using Clinical Pseudo-notes","date":"2024-01-31","arxiv_id":"2402.00160","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multimodal-clinical-pseudo-notes-for#ran","syntology_url":"https://syntology.ai/paper/2402.00160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00160"}},"official":{"repos":["Simonlee711/MEME"],"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/to-burst-or-not-to-burst-generating-and","slug":"to-burst-or-not-to-burst-generating-and","title":"To Burst or Not to Burst: Generating and Quantifying Improbable Text","date":"2024-01-27","arxiv_id":"2401.15476","repositories_listed":1,"syntology":null},{"url":"/paper/proxyqa-an-alternative-framework-for","slug":"proxyqa-an-alternative-framework-for","title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models","date":"2024-01-26","arxiv_id":"2401.15042","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-sensitivities-and-inconsistent","slug":"semantic-sensitivities-and-inconsistent","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","date":"2024-01-25","arxiv_id":"2401.14440","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-guided-knowledge-retrieval-and","slug":"consistency-guided-knowledge-retrieval-and","title":"Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction","date":"2024-01-24","arxiv_id":"2401.13598","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-contract-ner-using-instruction","slug":"fine-grained-contract-ner-using-instruction","title":"Fine-grained Contract NER using instruction based model","date":"2024-01-24","arxiv_id":"2401.13545","repositories_listed":1,"syntology":null},{"url":"/paper/towards-explainable-harmful-meme-detection","slug":"towards-explainable-harmful-meme-detection","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","date":"2024-01-24","arxiv_id":"2401.13298","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":1,"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/towards-explainable-harmful-meme-detection#ran","syntology_url":"https://syntology.ai/paper/2401.13298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13298"}},"official":{"repos":["hkbunlp/explainhm-www2024"],"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/an-empirical-analysis-of-in-context-learning","slug":"an-empirical-analysis-of-in-context-learning","title":"An Empirical Study of In-context Learning in LLMs for Machine Translation","date":"2024-01-22","arxiv_id":"2401.12097","repositories_listed":1,"syntology":null},{"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/self-training-from-self-memory-in-data-to","slug":"self-training-from-self-memory-in-data-to","title":"Self-training from Self-memory in Data-to-text Generation","date":"2024-01-19","arxiv_id":"2401.10567","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/sketch-guided-constrained-decoding-for","slug":"sketch-guided-constrained-decoding-for","title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","date":"2024-01-18","arxiv_id":"2401.09967","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"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) · 5 unverified","sample_list":"/paper/sketch-guided-constrained-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2401.09967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09967"}},"official":{"repos":["epfl-dlab/sketchgcd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-large-language-models-for-nlg","slug":"leveraging-large-language-models-for-nlg","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","date":"2024-01-13","arxiv_id":"2401.07103","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-can-learn-temporal","slug":"large-language-models-can-learn-temporal","title":"Large Language Models Can Learn Temporal Reasoning","date":"2024-01-12","arxiv_id":"2401.06853","repositories_listed":1,"syntology":{"n":27,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":15,"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) · 15 unverified","sample_list":"/paper/large-language-models-can-learn-temporal#ran","syntology_url":"https://syntology.ai/paper/2401.06853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06853"}},"official":{"repos":["xiongsiheng/tg-llm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":15,"ran_from_kinds":["official"]}}},{"url":"/paper/mugi-enhancing-information-retrieval-through","slug":"mugi-enhancing-information-retrieval-through","title":"Exploring the Best Practices of Query Expansion with Large Language Models","date":"2024-01-12","arxiv_id":"2401.06311","repositories_listed":1,"syntology":null},{"url":"/paper/pizzacommonsense-learning-to-model","slug":"pizzacommonsense-learning-to-model","title":"PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes","date":"2024-01-12","arxiv_id":"2401.06930","repositories_listed":1,"syntology":null},{"url":"/paper/generating-diverse-and-high-quality-texts-by","slug":"generating-diverse-and-high-quality-texts-by","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","date":"2024-01-10","arxiv_id":"2401.05054","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/generating-diverse-and-high-quality-texts-by#ran","syntology_url":"https://syntology.ai/paper/2401.05054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05054"}},"official":{"repos":["CyberAgentAILab/diverse-mbr"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deepspeed-fastgen-high-throughput-text","slug":"deepspeed-fastgen-high-throughput-text","title":"DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference","date":"2024-01-09","arxiv_id":"2401.08671","repositories_listed":1,"syntology":null},{"url":"/paper/luna-a-framework-for-language-understanding","slug":"luna-a-framework-for-language-understanding","title":"LUNA: A Framework for Language Understanding and Naturalness Assessment","date":"2024-01-09","arxiv_id":"2401.04522","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-spatial-reasoning-in-large-language","slug":"advancing-spatial-reasoning-in-large-language","title":"Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark","date":"2024-01-08","arxiv_id":"2401.03991","repositories_listed":1,"syntology":null},{"url":"/paper/hyperparameter-free-approach-for-faster","slug":"hyperparameter-free-approach-for-faster","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","date":"2024-01-05","arxiv_id":"2401.02749","repositories_listed":1,"syntology":null},{"url":"/paper/improving-natural-language-understanding-with","slug":"improving-natural-language-understanding-with","title":"ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion","date":"2024-01-04","arxiv_id":"2401.02993","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-survey-of-hallucination","slug":"a-comprehensive-survey-of-hallucination","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","date":"2024-01-02","arxiv_id":"2401.01313","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/a-comprehensive-survey-of-hallucination#ran","syntology_url":"https://syntology.ai/paper/2401.01313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01313"}},"official":null}},{"url":"/paper/cheetah-natural-language-generation-for-517","slug":"cheetah-natural-language-generation-for-517","title":"Cheetah: Natural Language Generation for 517 African Languages","date":"2024-01-02","arxiv_id":"2401.01053","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-structured-data-as-graph-for-data-to","slug":"unifying-structured-data-as-graph-for-data-to","title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","date":"2024-01-02","arxiv_id":"2401.01183","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-large-language-models-on","slug":"benchmarking-large-language-models-on","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","date":"2024-01-01","arxiv_id":"2401.00690","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/benchmarking-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2401.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00690"}},"official":{"repos":["xt-cyh/codi-eval"],"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"]}}}],"record_sha256":"2374a7d9a5e7ea47a2ffe0f7cbd582dc81df7403b2662f3772452e6ff7e7f14c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}