{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/large-language-model/papers/23","list_of":"/task/large-language-model","task":"Large Language Model","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":23,"pages_in_order":61,"rows_per_page":100,"rows":[2201,2300],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/large-language-model","prev":"/task/large-language-model/papers/22","next":"/task/large-language-model/papers/24","papers":[{"url":"/paper/what-makes-a-language-easy-to-deep-learn","slug":"what-makes-a-language-easy-to-deep-learn","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","date":"2023-02-23","arxiv_id":"2302.12239","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-makes-a-language-easy-to-deep-learn#ran","syntology_url":"https://syntology.ai/paper/2302.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12239"}},"official":{"repos":["lgalke/easy2deeplearn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-equitable-representation-in-text-to","slug":"towards-equitable-representation-in-text-to","title":"Towards Equitable Representation in Text-to-Image Synthesis Models with the Cross-Cultural Understanding Benchmark (CCUB) Dataset","date":"2023-01-28","arxiv_id":"2301.12073","repositories_listed":1,"syntology":null},{"url":"/paper/thoughtsource-a-central-hub-for-large","slug":"thoughtsource-a-central-hub-for-large","title":"ThoughtSource: A central hub for large language model reasoning data","date":"2023-01-27","arxiv_id":"2301.11596","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/thoughtsource-a-central-hub-for-large#ran","syntology_url":"https://syntology.ai/paper/2301.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11596"}},"official":{"repos":["openbiolink/thoughtsource"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/exaranker-explanation-augmented-neural-ranker","slug":"exaranker-explanation-augmented-neural-ranker","title":"ExaRanker: Explanation-Augmented Neural Ranker","date":"2023-01-25","arxiv_id":"2301.10521","repositories_listed":1,"syntology":null},{"url":"/paper/in-bloom-creativity-and-affinity-in","slug":"in-bloom-creativity-and-affinity-in","title":"In BLOOM: Creativity and Affinity in Artificial Lyrics and Art","date":"2023-01-13","arxiv_id":"2301.05402","repositories_listed":1,"syntology":null},{"url":"/paper/see-think-confirm-interactive-prompting","slug":"see-think-confirm-interactive-prompting","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","date":"2023-01-12","arxiv_id":"2301.05226","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-as-corporate-lobbyists","slug":"large-language-models-as-corporate-lobbyists","title":"Large Language Models as Corporate Lobbyists","date":"2023-01-03","arxiv_id":"2301.01181","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-with-retrieval-faithful-large","slug":"rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","arxiv_id":"2301.00303","repositories_listed":1,"syntology":null},{"url":"/paper/crowd-score-a-method-for-the-evaluation-of","slug":"crowd-score-a-method-for-the-evaluation-of","title":"Crowd Score: A Method for the Evaluation of Jokes using Large Language Model AI Voters as Judges","date":"2022-12-21","arxiv_id":"2212.11214","repositories_listed":1,"syntology":null},{"url":"/paper/deplot-one-shot-visual-language-reasoning-by","slug":"deplot-one-shot-visual-language-reasoning-by","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","date":"2022-12-20","arxiv_id":"2212.10505","repositories_listed":1,"syntology":null},{"url":"/paper/parsel-a-unified-natural-language-framework","slug":"parsel-a-unified-natural-language-framework","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","date":"2022-12-20","arxiv_id":"2212.10561","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parsel-a-unified-natural-language-framework#ran","syntology_url":"https://syntology.ai/paper/2212.10561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10561"}},"official":{"repos":["ezelikman/parsel"],"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/soda-million-scale-dialogue-distillation-with","slug":"soda-million-scale-dialogue-distillation-with","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","date":"2022-12-20","arxiv_id":"2212.10465","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/soda-million-scale-dialogue-distillation-with#ran","syntology_url":"https://syntology.ai/paper/2212.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10465"}},"official":{"repos":["skywalker023/sodaverse"],"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/very-large-language-model-as-a-unified","slug":"very-large-language-model-as-a-unified","title":"Very Large Language Model as a Unified Methodology of Text Mining","date":"2022-12-19","arxiv_id":"2212.09271","repositories_listed":1,"syntology":null},{"url":"/paper/visconde-multi-document-qa-with-gpt-3-and","slug":"visconde-multi-document-qa-with-gpt-3-and","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","date":"2022-12-19","arxiv_id":"2212.09656","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-role-of-scale-for-in-context","slug":"rethinking-the-role-of-scale-for-in-context","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","date":"2022-12-18","arxiv_id":"2212.09095","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-role-of-scale-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2212.09095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09095"}},"official":{"repos":["amazon-science/llm-interpret"],"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/claim-optimization-in-computational","slug":"claim-optimization-in-computational","title":"Claim Optimization in Computational Argumentation","date":"2022-12-17","arxiv_id":"2212.08913","repositories_listed":1,"syntology":null},{"url":"/paper/deepdfa-dataflow-analysis-guided-efficient","slug":"deepdfa-dataflow-analysis-guided-efficient","title":"Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection","date":"2022-12-15","arxiv_id":"2212.08108","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepdfa-dataflow-analysis-guided-efficient#ran","syntology_url":"https://syntology.ai/paper/2212.08108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08108"}},"official":{"repos":["ISU-PAAL/DeepDFA"],"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/on-second-thought-let-s-not-think-step-by","slug":"on-second-thought-let-s-not-think-step-by","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","date":"2022-12-15","arxiv_id":"2212.08061","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-second-thought-let-s-not-think-step-by#ran","syntology_url":"https://syntology.ai/paper/2212.08061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08061"}},"official":{"repos":["salt-nlp/chain-of-thought-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/deepspeed-data-efficiency-improving-deep","slug":"deepspeed-data-efficiency-improving-deep","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","date":"2022-12-07","arxiv_id":"2212.03597","repositories_listed":1,"syntology":null},{"url":"/paper/conal-anticipating-outliers-with-large","slug":"conal-anticipating-outliers-with-large","title":"Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models","date":"2022-11-28","arxiv_id":"2211.15718","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conal-anticipating-outliers-with-large#ran","syntology_url":"https://syntology.ai/paper/2211.15718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15718"}},"official":{"repos":["albertkx/conal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","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/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"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/memonet-memorizing-representations-of-all","slug":"memonet-memorizing-representations-of-all","title":"MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction","date":"2022-10-25","arxiv_id":"2211.01334","repositories_listed":1,"syntology":null},{"url":"/paper/code4struct-code-generation-for-few-shot","slug":"code4struct-code-generation-for-few-shot","title":"Code4Struct: Code Generation for Few-Shot Event Structure Prediction","date":"2022-10-23","arxiv_id":"2210.12810","repositories_listed":1,"syntology":null},{"url":"/paper/tabllm-few-shot-classification-of-tabular","slug":"tabllm-few-shot-classification-of-tabular","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","date":"2022-10-19","arxiv_id":"2210.10723","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/tabllm-few-shot-classification-of-tabular#ran","syntology_url":"https://syntology.ai/paper/2210.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10723"}},"official":{"repos":["clinicalml/TabLLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/arithmetic-sampling-parallel-diverse-decoding","slug":"arithmetic-sampling-parallel-diverse-decoding","title":"Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models","date":"2022-10-18","arxiv_id":"2210.15458","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/arithmetic-sampling-parallel-diverse-decoding#ran","syntology_url":"https://syntology.ai/paper/2210.15458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15458"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/core-a-retrieve-then-edit-framework-for","slug":"core-a-retrieve-then-edit-framework-for","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","date":"2022-10-10","arxiv_id":"2210.04873","repositories_listed":1,"syntology":null},{"url":"/paper/controllable-dialogue-simulation-with-in","slug":"controllable-dialogue-simulation-with-in","title":"Controllable Dialogue Simulation with In-Context Learning","date":"2022-10-09","arxiv_id":"2210.04185","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-pretty-good-zero","slug":"large-language-models-are-pretty-good-zero","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","date":"2022-10-05","arxiv_id":"2210.02506","repositories_listed":1,"syntology":null},{"url":"/paper/when-to-make-exceptions-exploring-language","slug":"when-to-make-exceptions-exploring-language","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","date":"2022-10-04","arxiv_id":"2210.01478","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-to-make-exceptions-exploring-language#ran","syntology_url":"https://syntology.ai/paper/2210.01478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01478"}},"official":{"repos":["feradauto/moralcot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-answer-semantic-queries-over-code","slug":"learning-to-answer-semantic-queries-over-code","title":"CodeQueries: A Dataset of Semantic Queries over Code","date":"2022-09-17","arxiv_id":"2209.08372","repositories_listed":1,"syntology":null},{"url":"/paper/do-large-language-models-know-what-humans","slug":"do-large-language-models-know-what-humans","title":"Do Large Language Models know what humans know?","date":"2022-09-04","arxiv_id":"2209.01515","repositories_listed":1,"syntology":null},{"url":"/paper/selective-text-augmentation-with-word-roles","slug":"selective-text-augmentation-with-word-roles","title":"Selective Text Augmentation with Word Roles for Low-Resource Text Classification","date":"2022-09-04","arxiv_id":"2209.01560","repositories_listed":1,"syntology":null},{"url":"/paper/folio-natural-language-reasoning-with-first","slug":"folio-natural-language-reasoning-with-first","title":"FOLIO: Natural Language Reasoning with First-Order Logic","date":"2022-09-02","arxiv_id":"2209.00840","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompting-as-probing-using-language-models#ran","syntology_url":"https://syntology.ai/paper/2208.11057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11057"}},"official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vault-augmenting-the-vision-and-language","slug":"vault-augmenting-the-vision-and-language","title":"VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media","date":"2022-08-18","arxiv_id":"2208.09021","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/vault-augmenting-the-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2208.09021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.09021"}},"official":{"repos":["gchochla/vault"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/coditt5-pretraining-for-source-code-and","slug":"coditt5-pretraining-for-source-code-and","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","date":"2022-08-10","arxiv_id":"2208.05446","repositories_listed":1,"syntology":null},{"url":"/paper/solving-quantitative-reasoning-problems-with","slug":"solving-quantitative-reasoning-problems-with","title":"Solving Quantitative Reasoning Problems with Language Models","date":"2022-06-29","arxiv_id":"2206.14858","repositories_listed":1,"syntology":null},{"url":"/paper/putting-gpt-3-s-creativity-to-the-alternative","slug":"putting-gpt-3-s-creativity-to-the-alternative","title":"Putting GPT-3's Creativity to the (Alternative Uses) Test","date":"2022-06-10","arxiv_id":"2206.08932","repositories_listed":1,"syntology":null},{"url":"/paper/housekeep-tidying-virtual-households-using","slug":"housekeep-tidying-virtual-households-using","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","date":"2022-05-22","arxiv_id":"2205.10712","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/housekeep-tidying-virtual-households-using#ran","syntology_url":"https://syntology.ai/paper/2205.10712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10712"}},"official":{"repos":["yashkant/housekeep"],"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/rankgen-improving-text-generation-with-large","slug":"rankgen-improving-text-generation-with-large","title":"RankGen: Improving Text Generation with Large Ranking Models","date":"2022-05-19","arxiv_id":"2205.09726","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/rankgen-improving-text-generation-with-large#ran","syntology_url":"https://syntology.ai/paper/2205.09726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09726"}},"official":{"repos":["martiansideofthemoon/rankgen"],"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/the-unreliability-of-explanations-in-few-shot","slug":"the-unreliability-of-explanations-in-few-shot","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","date":"2022-05-06","arxiv_id":"2205.03401","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-image-to-text-generation-for-visual","slug":"zero-shot-image-to-text-generation-for-visual","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","date":"2021-11-29","arxiv_id":"2111.14447","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/zero-shot-image-to-text-generation-for-visual#ran","syntology_url":"https://syntology.ai/paper/2111.14447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14447"}},"official":{"repos":["yoadtew/zero-shot-image-to-text"],"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/the-klarna-product-page-dataset-a","slug":"the-klarna-product-page-dataset-a","title":"The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models","date":"2021-11-03","arxiv_id":"2111.02168","repositories_listed":1,"syntology":null},{"url":"/paper/darmok-and-jalad-at-tanagra-a-dataset-and","slug":"darmok-and-jalad-at-tanagra-a-dataset-and","title":"Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language","date":"2021-07-16","arxiv_id":"2107.08146","repositories_listed":1,"syntology":null},{"url":"/paper/a-brief-study-on-the-effects-of-training","slug":"a-brief-study-on-the-effects-of-training","title":"A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss","date":"2021-06-20","arxiv_id":"2106.10619","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-break-prediction-with-bidirectional","slug":"phrase-break-prediction-with-bidirectional","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","date":"2021-04-26","arxiv_id":"2104.12395","repositories_listed":1,"syntology":null},{"url":"/paper/km-bart-knowledge-enhanced-multimodal-bart","slug":"km-bart-knowledge-enhanced-multimodal-bart","title":"KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation","date":"2021-01-02","arxiv_id":"2101.00419","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-contrastive-learning-for-pre-1","slug":"supervised-contrastive-learning-for-pre-1","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","date":"2020-11-03","arxiv_id":"2011.01403","repositories_listed":1,"syntology":null},{"url":"/paper/plug-and-play-conversational-models","slug":"plug-and-play-conversational-models","title":"Plug-and-Play Conversational Models","date":"2020-10-09","arxiv_id":"2010.04344","repositories_listed":1,"syntology":null},{"url":"/paper/citation-text-generation","slug":"citation-text-generation","title":"Explaining Relationships Between Scientific Documents","date":"2020-02-02","arxiv_id":"2002.00317","repositories_listed":1,"syntology":null},{"url":null,"slug":"dense-longitudinal-progress-note-generation","title":"DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits","date":"2025-07-18","arxiv_id":"2507.14079","repositories_listed":0,"syntology":null},{"url":null,"slug":"georeg-weight-constrained-few-shot-regression","title":"GeoReg: Weight-Constrained Few-Shot Regression for Socio-Economic Estimation using LLM","date":"2025-07-17","arxiv_id":"2507.13323","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-reinforcement-learning-meets-large","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","date":"2025-07-17","arxiv_id":"2507.13158","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-the-embodied-gap-in-vision-and","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","date":"2025-07-17","arxiv_id":"2507.13019","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-generative-energy-arena-gea-incorporating","title":"The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations","date":"2025-07-17","arxiv_id":"2507.13302","repositories_listed":0,"syntology":null},{"url":null,"slug":"draw-an-ugly-person-an-exploration-of","title":"Draw an Ugly Person An Exploration of Generative AIs Perceptions of Ugliness","date":"2025-07-16","arxiv_id":"2507.12212","repositories_listed":0,"syntology":null},{"url":null,"slug":"kptllm-towards-generic-keypoint-comprehension","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","date":"2025-07-15","arxiv_id":"2507.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"lilm-rdb-sfc-lightweight-language-model-with","title":"LiLM-RDB-SFC: Lightweight Language Model with Relational Database-Guided DRL for Optimized SFC Provisioning","date":"2025-07-15","arxiv_id":"2507.10903","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrcti-a-large-language-model-based-framework","title":"LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification","date":"2025-07-15","arxiv_id":"2507.11310","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrmr-llm-driven-relational-multi-node-ranking","title":"LRMR: LLM-Driven Relational Multi-node Ranking for Lymph Node Metastasis Assessment in Rectal Cancer","date":"2025-07-15","arxiv_id":"2507.11457","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-experts-in-large-language-models","title":"Mixture of Experts in Large Language Models","date":"2025-07-15","arxiv_id":"2507.11181","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-playing-llm-based-multi-agent-support","title":"Role-Playing LLM-Based Multi-Agent Support Framework for Detecting and Addressing Family Communication Bias","date":"2025-07-15","arxiv_id":"2507.11210","repositories_listed":0,"syntology":null},{"url":null,"slug":"tactical-decision-for-multi-ugv-confrontation","title":"Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander","date":"2025-07-15","arxiv_id":"2507.11079","repositories_listed":0,"syntology":null},{"url":null,"slug":"chat-with-ai-the-surprising-turn-of-real-time","title":"Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI","date":"2025-07-14","arxiv_id":"2507.10510","repositories_listed":0,"syntology":null},{"url":null,"slug":"iceberg-enhancing-hls-modeling-with-synthetic","title":"Iceberg: Enhancing HLS Modeling with Synthetic Data","date":"2025-07-14","arxiv_id":"2507.09948","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlar-multi-layer-large-language-model-based","title":"MLAR: Multi-layer Large Language Model-based Robotic Process Automation Applicant Tracking","date":"2025-07-14","arxiv_id":"2507.10472","repositories_listed":0,"syntology":null},{"url":null,"slug":"posellm-enhancing-language-guided-human-pose","title":"PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment","date":"2025-07-12","arxiv_id":"2507.09139","repositories_listed":0,"syntology":null},{"url":null,"slug":"kat-v1-kwai-autothink-technical-report","title":"KAT-V1: Kwai-AutoThink Technical Report","date":"2025-07-11","arxiv_id":"2507.08297","repositories_listed":0,"syntology":null},{"url":null,"slug":"sand-boosting-llm-agents-with-self-taught","title":"SAND: Boosting LLM Agents with Self-Taught Action Deliberation","date":"2025-07-10","arxiv_id":"2507.07441","repositories_listed":0,"syntology":null},{"url":null,"slug":"skip-a-layer-or-loop-it-test-time-depth","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","date":"2025-07-10","arxiv_id":"2507.07996","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-representation-framework-with-llm","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","date":"2025-07-09","arxiv_id":"2507.06719","repositories_listed":0,"syntology":null},{"url":null,"slug":"gnn-vitcap-gnn-enhanced-multiple-instance","title":"GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning","date":"2025-07-09","arxiv_id":"2507.07006","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeeze-the-soaked-sponge-efficient-off","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","date":"2025-07-09","arxiv_id":"2507.06892","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dark-side-of-llms-agent-based-attacks-for","title":"The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover","date":"2025-07-09","arxiv_id":"2507.06850","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-synthesis-of-high-quality-triplet","title":"Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval","date":"2025-07-08","arxiv_id":"2507.05970","repositories_listed":0,"syntology":null},{"url":null,"slug":"bluelm-2-5-3b-technical-report","title":"BlueLM-2.5-3B Technical Report","date":"2025-07-08","arxiv_id":"2507.05934","repositories_listed":0,"syntology":null},{"url":null,"slug":"cavgan-unifying-jailbreak-and-defense-of-llms","title":"CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations","date":"2025-07-08","arxiv_id":"2507.06043","repositories_listed":0,"syntology":null},{"url":null,"slug":"lead-the-llm-enhanced-planning-system","title":"LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving","date":"2025-07-08","arxiv_id":"2507.05754","repositories_listed":0,"syntology":null},{"url":null,"slug":"prefixagent-an-llm-powered-design-framework","title":"PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization","date":"2025-07-08","arxiv_id":"2507.06127","repositories_listed":0,"syntology":null},{"url":null,"slug":"recrankereval-a-flexible-and-extensible","title":"RecRankerEval: A Flexible and Extensible Framework for Top-k LLM-based Recommendation","date":"2025-07-08","arxiv_id":"2507.05880","repositories_listed":0,"syntology":null},{"url":null,"slug":"talkfashion-intelligent-virtual-try-on","title":"TalkFashion: Intelligent Virtual Try-On Assistant Based on Multimodal Large Language Model","date":"2025-07-08","arxiv_id":"2507.05790","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-event-reasoning-and-prediction-by","title":"Video Event Reasoning and Prediction by Fusing World Knowledge from LLMs with Vision Foundation Models","date":"2025-07-08","arxiv_id":"2507.05822","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-generated-text-detection-using-instruction","title":"AI Generated Text Detection Using Instruction Fine-tuned Large Language and Transformer-Based Models","date":"2025-07-07","arxiv_id":"2507.05157","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepretro-retrosynthetic-pathway-discovery","title":"DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning","date":"2025-07-07","arxiv_id":"2507.07060","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-memory-in-llm-agents-via","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","date":"2025-07-07","arxiv_id":"2507.05257","repositories_listed":0,"syntology":null},{"url":null,"slug":"inaugural-moasei-competition-at-aamas-2025-a","title":"Inaugural MOASEI Competition at AAMAS'2025: A Technical Report","date":"2025-07-07","arxiv_id":"2507.05469","repositories_listed":0,"syntology":null},{"url":null,"slug":"prime-large-language-model-personalization","title":"PRIME: Large Language Model Personalization with Cognitive Memory and Thought Processes","date":"2025-07-07","arxiv_id":"2507.04607","repositories_listed":0,"syntology":null},{"url":null,"slug":"bifair-a-fairness-aware-training-framework","title":"BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization","date":"2025-07-06","arxiv_id":"2507.04294","repositories_listed":0,"syntology":null},{"url":null,"slug":"cot-lized-diffusion-let-s-reinforce-t2i","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","date":"2025-07-06","arxiv_id":"2507.04451","repositories_listed":0,"syntology":null},{"url":null,"slug":"behaviour-space-analysis-of-llm-driven-meta","title":"Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery","date":"2025-07-04","arxiv_id":"2507.03605","repositories_listed":0,"syntology":null},{"url":null,"slug":"graft-a-graph-based-flow-aware-agentic","title":"GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation","date":"2025-07-04","arxiv_id":"2507.03311","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-disentanglement-via-language-guidance","title":"Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization","date":"2025-07-03","arxiv_id":"2507.02288","repositories_listed":0,"syntology":null},{"url":null,"slug":"opentable-r1-a-reinforcement-learning","title":"OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering","date":"2025-07-02","arxiv_id":"2507.03018","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-ta-towards-scalable-automated-thematic","title":"Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning","date":"2025-06-30","arxiv_id":"2506.23998","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-aware-text-to-image-retrieval-referring","title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","date":"2025-06-28","arxiv_id":"2506.22864","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-empowered-agent-for","title":"A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis","date":"2025-06-27","arxiv_id":"2507.02938","repositories_listed":0,"syntology":null},{"url":null,"slug":"arag-agentic-retrieval-augmented-generation","title":"ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation","date":"2025-06-27","arxiv_id":"2506.21931","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-consciousness-be-observed-from-large","title":"Can \"consciousness\" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis","date":"2025-06-26","arxiv_id":"2506.22516","repositories_listed":0,"syntology":null},{"url":null,"slug":"groundflow-a-plug-in-module-for-temporal","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","date":"2025-06-26","arxiv_id":"2506.21188","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-agent-for-modular-task","title":"Large Language Model Agent for Modular Task Execution in Drug Discovery","date":"2025-06-26","arxiv_id":"2507.02925","repositories_listed":0,"syntology":null}],"record_sha256":"f949540d32fdafa6271bd72225472480e47dfe846cc377a7232ee75a414fbf3e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}