{"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":"/method/linear-warmup-with-cosine-annealing/papers/25","list_of":"/method/linear-warmup-with-cosine-annealing","method":"Linear Warmup With Cosine Annealing","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":25,"pages_in_order":38,"rows_per_page":100,"rows":[2401,2500],"of":3797,"counts":{"archive_papers_tagged":3797,"with_a_code_link":1655,"where_syntology_ran_a_sample":602,"not_listed_spam_title":0,"listed":3797,"listed_where_code_ran":602,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":490,"every_run_a_failure_of_syntologys_instrument":112,"listed_with_a_run_with_no_instrument_failure":490,"listed_every_run_a_failure_of_syntologys_instrument":112,"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":"/method/linear-warmup-with-cosine-annealing","prev":"/method/linear-warmup-with-cosine-annealing/papers/24","next":"/method/linear-warmup-with-cosine-annealing/papers/26","papers":[{"paper":"/paper/inrank-incremental-low-rank-learning","slug":"inrank-incremental-low-rank-learning","title":"InRank: Incremental Low-Rank Learning","date":"2023-06-20","arxiv_id":"2306.11250","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-better-than-your-llm","slug":"learning-to-generate-better-than-your-llm","title":"Learning to Generate Better Than Your LLM","date":"2023-06-20","arxiv_id":"2306.11816","n_code_links":1,"syntology":null},{"paper":null,"slug":"textbooks-are-all-you-need","title":"Textbooks Are All You Need","date":"2023-06-20","arxiv_id":"2306.11644","n_code_links":0,"syntology":null},{"paper":"/paper/a-preliminary-study-of-chatgpt-on-news","slug":"a-preliminary-study-of-chatgpt-on-news","title":"A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News","date":"2023-06-19","arxiv_id":"2306.10702","n_code_links":1,"syntology":null},{"paper":"/paper/bayling-bridging-cross-lingual-alignment-and","slug":"bayling-bridging-cross-lingual-alignment-and","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","date":"2023-06-19","arxiv_id":"2306.10968","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-sequential-recommendation-with","title":"Generative Sequential Recommendation with GPTRec","date":"2023-06-19","arxiv_id":"2306.11114","n_code_links":0,"syntology":null},{"paper":null,"slug":"synergpt-in-context-learning-for-personalized","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","date":"2023-06-19","arxiv_id":"2307.11694","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using","slug":"enhancing-social-network-hate-detection-using","title":"Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time","date":"2023-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/demystifying-gpt-self-repair-for-code","slug":"demystifying-gpt-self-repair-for-code","title":"Is Self-Repair a Silver Bullet for Code Generation?","date":"2023-06-16","arxiv_id":"2306.09896","n_code_links":1,"syntology":null},{"paper":"/paper/gpt4-is-slightly-helpful-for-peer-review","slug":"gpt4-is-slightly-helpful-for-peer-review","title":"GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study","date":"2023-06-16","arxiv_id":"2307.05492","n_code_links":2,"syntology":null},{"paper":"/paper/chessgpt-bridging-policy-learning-and-1","slug":"chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","arxiv_id":"2306.09200","n_code_links":1,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["waterhorse1/chessgpt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/explore-establish-exploit-red-teaming","slug":"explore-establish-exploit-red-teaming","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","date":"2023-06-15","arxiv_id":"2306.09442","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["algorithmic-alignment-lab/commonclaim","thestephencasper/common_claim","thestephencasper/explore_establish_exploit_llms"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"exploring-the-mit-mathematics-and-eecs","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","date":"2023-06-15","arxiv_id":"2306.08997","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-pop-song-generator-designing-an-online","title":"The pop song generator: designing an online course to teach collaborative, creative AI","date":"2023-06-15","arxiv_id":"2306.10069","n_code_links":0,"syntology":null},{"paper":null,"slug":"thrilled-by-your-progress-large-language","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","date":"2023-06-15","arxiv_id":"2306.10073","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-the-effectiveness-of-gpt-3-in","slug":"assessing-the-effectiveness-of-gpt-3-in","title":"Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset","date":"2023-06-14","arxiv_id":"2306.08190","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-agi-in-computer-vision-lessons","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","date":"2023-06-14","arxiv_id":"2306.08641","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-few-shot-learning-from-natural-language","title":"FLamE: Few-shot Learning from Natural Language Explanations","date":"2023-06-13","arxiv_id":"2306.08042","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-like-intuitive-behavior-and-reasoning","title":"Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4","date":"2023-06-13","arxiv_id":"2306.07622","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-n-gram-approximation-of-pre-trained","title":"On the N-gram Approximation of Pre-trained Language Models","date":"2023-06-12","arxiv_id":"2306.06892","n_code_links":0,"syntology":null},{"paper":"/paper/recursion-of-thought-a-divide-and-conquer","slug":"recursion-of-thought-a-divide-and-conquer","title":"Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models","date":"2023-06-12","arxiv_id":"2306.06891","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-bea-2023-shared-task-on-generating-ai","title":"The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-12","arxiv_id":"2306.06941","n_code_links":0,"syntology":null},{"paper":"/paper/waffling-around-for-performance-visual","slug":"waffling-around-for-performance-visual","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","date":"2023-06-12","arxiv_id":"2306.07282","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["explainableml/waffleclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/inductive-reasoning-in-humans-and-large","slug":"inductive-reasoning-in-humans-and-large","title":"Inductive reasoning in humans and large language models","date":"2023-06-11","arxiv_id":"2306.06548","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-responses-of-large-language","title":"Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests","date":"2023-06-09","arxiv_id":"2306.05715","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-calls-enhancing-call-segmentation-and","title":"GPT-Calls: Enhancing Call Segmentation and Tagging by Generating Synthetic Conversations via Large Language Models","date":"2023-06-09","arxiv_id":"2306.07941","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-can-learn-exceptions-to","slug":"language-models-can-learn-exceptions-to","title":"Language Models Can Learn Exceptions to Syntactic Rules","date":"2023-06-09","arxiv_id":"2306.05969","n_code_links":1,"syntology":null},{"paper":"/paper/prodigy-an-expeditiously-adaptive-parameter","slug":"prodigy-an-expeditiously-adaptive-parameter","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","date":"2023-06-09","arxiv_id":"2306.06101","n_code_links":1,"syntology":null},{"paper":"/paper/reliability-check-an-analysis-of-gpt-3-s","slug":"reliability-check-an-analysis-of-gpt-3-s","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","date":"2023-06-09","arxiv_id":"2306.06199","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-telecom-language-through-large","title":"Understanding Telecom Language Through Large Language Models","date":"2023-06-09","arxiv_id":"2306.07933","n_code_links":0,"syntology":null},{"paper":"/paper/pandalm-an-automatic-evaluation-benchmark-for","slug":"pandalm-an-automatic-evaluation-benchmark-for","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","date":"2023-06-08","arxiv_id":"2306.05087","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"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","official":{"repos":["weopenml/pandalm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/prefer-to-classify-improving-text-classifiers","slug":"prefer-to-classify-improving-text-classifiers","title":"Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning","date":"2023-06-08","arxiv_id":"2306.04925","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["minnesotanlp/p2c"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-adaio-system-at-the-bea-2023-shared-task","title":"The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-08","arxiv_id":"2306.05360","n_code_links":0,"syntology":null},{"paper":"/paper/toolalpaca-generalized-tool-learning-for","slug":"toolalpaca-generalized-tool-learning-for","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","date":"2023-06-08","arxiv_id":"2306.05301","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["tangqiaoyu/ToolAlpaca"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/check-me-if-you-can-detecting-chatgpt","slug":"check-me-if-you-can-detecting-chatgpt","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","date":"2023-06-07","arxiv_id":"2306.05524","n_code_links":2,"syntology":null},{"paper":"/paper/good-data-large-data-or-no-data-comparing","slug":"good-data-large-data-or-no-data-comparing","title":"Good Data, Large Data, or No Data? Comparing Three Approaches in Developing Research Aspect Classifiers for Biomedical Papers","date":"2023-06-07","arxiv_id":"2306.04820","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-self-supervision-for-a-better-data","title":"GPT Self-Supervision for a Better Data Annotator","date":"2023-06-07","arxiv_id":"2306.04349","n_code_links":0,"syntology":null},{"paper":null,"slug":"personality-testing-of-gpt-3-limited-temporal","title":"Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality","date":"2023-06-07","arxiv_id":"2306.04308","n_code_links":0,"syntology":null},{"paper":null,"slug":"sciencebenchmark-a-complex-real-world","title":"ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems","date":"2023-06-07","arxiv_id":"2306.04743","n_code_links":0,"syntology":null},{"paper":"/paper/the-two-word-test-a-semantic-benchmark-for","slug":"the-two-word-test-a-semantic-benchmark-for","title":"The Two Word Test: A Semantic Benchmark for Large Language Models","date":"2023-06-07","arxiv_id":"2306.04610","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-analysis-of-parameter-efficient","slug":"an-empirical-analysis-of-parameter-efficient","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.04067","n_code_links":1,"syntology":null},{"paper":"/paper/certified-reasoning-with-language-models","slug":"certified-reasoning-with-language-models","title":"Certified Deductive Reasoning with Language Models","date":"2023-06-06","arxiv_id":"2306.04031","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"iterative-translation-refinement-with-large","title":"Iterative Translation Refinement with Large Language Models","date":"2023-06-06","arxiv_id":"2306.03856","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-acquisition-do-children-and-language","title":"Language acquisition: do children and language models follow similar learning stages?","date":"2023-06-06","arxiv_id":"2306.03586","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-syntactic-generalization-capacity","title":"Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion","date":"2023-06-05","arxiv_id":"2306.03055","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-as-a-mapping-assistant-a-novel-method","title":"ChatGPT as a mapping assistant: A novel method to enrich maps with generative AI and content derived from street-level photographs","date":"2023-06-05","arxiv_id":"2306.03204","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-gpt-model-pre-training-using-tensor","title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation","date":"2023-06-05","arxiv_id":"2306.02697","n_code_links":0,"syntology":null},{"paper":null,"slug":"stack-over-flowing-with-results-the-case-for","title":"Skill over Scale: The Case for Medium, Domain-Specific Models for SE","date":"2023-06-05","arxiv_id":"2306.03268","n_code_links":0,"syntology":null},{"paper":"/paper/auto-gpt-for-online-decision-making","slug":"auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","arxiv_id":"2306.02224","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":4,"phrase":"6 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["younghuman/llmagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-coding-social-science-datasets-with-1","title":"Towards Coding Social Science Datasets with Language Models","date":"2023-06-03","arxiv_id":"2306.02177","n_code_links":0,"syntology":null},{"paper":"/paper/can-contextual-biasing-remain-effective-with","slug":"can-contextual-biasing-remain-effective-with","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","date":"2023-06-02","arxiv_id":"2306.01942","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-glossary-of-clinical-terminology-a","title":"Automatic Glossary of Clinical Terminology: a Large-Scale Dictionary of Biomedical Definitions Generated from Ontological Knowledge","date":"2023-06-01","arxiv_id":"2306.00665","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-programming-etextbooks-with-chatgpt","title":"Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions","date":"2023-06-01","arxiv_id":"2306.00551","n_code_links":0,"syntology":null},{"paper":"/paper/multi-dimensional-evaluation-of-text","slug":"multi-dimensional-evaluation-of-text","title":"Multi-Dimensional Evaluation of Text Summarization with In-Context Learning","date":"2023-06-01","arxiv_id":"2306.01200","n_code_links":1,"syntology":null},{"paper":null,"slug":"systematic-evaluation-of-gpt-3-for-zero-shot","title":"Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation","date":"2023-06-01","arxiv_id":"2306.01183","n_code_links":0,"syntology":null},{"paper":null,"slug":"topex-topic-based-explanations-for-model","title":"TopEx: Topic-based Explanations for Model Comparison","date":"2023-06-01","arxiv_id":"2306.00976","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gpt-s-programming-capability","title":"Evaluating GPT's Programming Capability through CodeWars' Katas","date":"2023-05-31","arxiv_id":"2306.01784","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-emergence-of-deductive","title":"Examining the Emergence of Deductive Reasoning in Generative Language Models","date":"2023-05-31","arxiv_id":"2306.01009","n_code_links":0,"syntology":null},{"paper":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-base-question-answering-for-space","slug":"knowledge-base-question-answering-for-space","title":"Knowledge Base Question Answering for Space Debris Queries","date":"2023-05-31","arxiv_id":"2305.19734","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-conceptual-representation-require","title":"Does Conceptual Representation Require Embodiment? Insights From Large Language Models","date":"2023-05-30","arxiv_id":"2305.19103","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-select-open-ended-visual","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","date":"2023-05-30","arxiv_id":"2305.18842","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-models-in-construction-industry","title":"GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation","date":"2023-05-30","arxiv_id":"2305.18997","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-seeds-beyond-weeds-green-teaming","title":"Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses","date":"2023-05-30","arxiv_id":"2306.03097","n_code_links":0,"syntology":null},{"paper":"/paper/check-covid-fact-checking-covid-19-news","slug":"check-covid-fact-checking-covid-19-news","title":"Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence","date":"2023-05-29","arxiv_id":"2305.18265","n_code_links":1,"syntology":null},{"paper":null,"slug":"coeditor-leveraging-contextual-changes-for","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","date":"2023-05-29","arxiv_id":"2305.18584","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-they-don-t","slug":"do-large-language-models-know-what-they-don-t","title":"Do Large Language Models Know What They Don't Know?","date":"2023-05-29","arxiv_id":"2305.18153","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yinzhangyue/selfaware"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-effectiveness-of-gpt-3-in","title":"Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods","date":"2023-05-29","arxiv_id":"2305.18156","n_code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","n_code_links":1,"syntology":null},{"paper":"/paper/marked-personas-using-natural-language","slug":"marked-personas-using-natural-language","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","date":"2023-05-29","arxiv_id":"2305.18189","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["myracheng/markedpersonas"],"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"]}}},{"paper":null,"slug":"processgpt-transforming-business-process","title":"ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence","date":"2023-05-29","arxiv_id":"2306.01771","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-and-semantics-meet-in-the-middle","slug":"syntax-and-semantics-meet-in-the-middle","title":"Syntax and Semantics Meet in the \"Middle\": Probing the Syntax-Semantics Interface of LMs Through Agentivity","date":"2023-05-29","arxiv_id":"2305.18185","n_code_links":1,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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","official":{"repos":["socialfoundations/tttlm"],"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"]}}},{"paper":null,"slug":"transformer-language-models-handle-word","title":"Transformer Language Models Handle Word Frequency in Prediction Head","date":"2023-05-29","arxiv_id":"2305.18294","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-language-barriers-with-a-leap","title":"Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs","date":"2023-05-28","arxiv_id":"2305.17740","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-gpt-3-generated-explanations-for","slug":"evaluating-gpt-3-generated-explanations-for","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","date":"2023-05-28","arxiv_id":"2305.17680","n_code_links":1,"syntology":null},{"paper":"/paper/generating-edu-extracts-for-plan-guided","slug":"generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","date":"2023-05-28","arxiv_id":"2305.17779","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":0,"n_instrument":6,"unverified":4,"pointer_only":10,"phrase":"6 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["griff4692/edu-sum"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/kosbi-a-dataset-for-mitigating-social-bias","slug":"kosbi-a-dataset-for-mitigating-social-bias","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","date":"2023-05-28","arxiv_id":"2305.17701","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-label-biases-for-in-context","slug":"mitigating-label-biases-for-in-context","title":"Mitigating Label Biases for In-context Learning","date":"2023-05-28","arxiv_id":"2305.19148","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["fywalter/label-bias"],"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"]}}},{"paper":"/paper/square-a-large-scale-dataset-of-sensitive","slug":"square-a-large-scale-dataset-of-sensitive","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","date":"2023-05-28","arxiv_id":"2305.17696","n_code_links":1,"syntology":null},{"paper":null,"slug":"transfer-learning-for-power-outage-detection","title":"Transfer Learning for Power Outage Detection Task with Limited Training Data","date":"2023-05-28","arxiv_id":"2305.17817","n_code_links":0,"syntology":null},{"paper":null,"slug":"complementary-and-integrative-health-lexicon","title":"Complementary and Integrative Health Lexicon (CIHLex) and Entity Recognition in the Literature","date":"2023-05-27","arxiv_id":"2305.17353","n_code_links":0,"syntology":null},{"paper":"/paper/dna-gpt-divergent-n-gram-analysis-for","slug":"dna-gpt-divergent-n-gram-analysis-for","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","date":"2023-05-27","arxiv_id":"2305.17359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["xianjun-yang/dna-gpt"],"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"]}}},{"paper":"/paper/model-dementia-generated-data-makes-models","slug":"model-dementia-generated-data-makes-models","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","date":"2023-05-27","arxiv_id":"2305.17493","n_code_links":1,"syntology":null},{"paper":"/paper/towards-explainable-conversational","slug":"towards-explainable-conversational","title":"Towards Explainable Conversational Recommender Systems","date":"2023-05-27","arxiv_id":"2305.18363","n_code_links":1,"syntology":null},{"paper":"/paper/what-can-large-language-models-do-in","slug":"what-can-large-language-models-do-in","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","date":"2023-05-27","arxiv_id":"2305.18365","n_code_links":1,"syntology":null},{"paper":"/paper/backpack-language-models","slug":"backpack-language-models","title":"Backpack Language Models","date":"2023-05-26","arxiv_id":"2305.16765","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/chain-of-thought-hub-a-continuous-effort-to","slug":"chain-of-thought-hub-a-continuous-effort-to","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","date":"2023-05-26","arxiv_id":"2305.17306","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["franxyao/chain-of-thought-hub"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"chatgpt-a-study-on-its-utility-for-ubiquitous","title":"ChatGPT: A Study on its Utility for Ubiquitous Software Engineering Tasks","date":"2023-05-26","arxiv_id":"2305.16837","n_code_links":0,"syntology":null},{"paper":"/paper/counterfactual-reasoning-testing-language","slug":"counterfactual-reasoning-testing-language","title":"Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios","date":"2023-05-26","arxiv_id":"2305.16572","n_code_links":1,"syntology":null},{"paper":null,"slug":"distinguishing-human-generated-text-from","title":"Distinguishing Human Generated Text From ChatGPT Generated Text Using Machine Learning","date":"2023-05-26","arxiv_id":"2306.01761","n_code_links":0,"syntology":null},{"paper":"/paper/do-gpts-produce-less-literal-translations","slug":"do-gpts-produce-less-literal-translations","title":"Do GPTs Produce Less Literal Translations?","date":"2023-05-26","arxiv_id":"2305.16806","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-question-generation-needs-more","title":"Evaluation of Question Generation Needs More References","date":"2023-05-26","arxiv_id":"2305.16626","n_code_links":0,"syntology":null},{"paper":null,"slug":"impossible-distillation-from-low-quality","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","date":"2023-05-26","arxiv_id":"2305.16635","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-accuracy-of-gpt-3-4-results-on","title":"Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model","date":"2023-05-26","arxiv_id":"2305.17116","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-as-tool-makers","slug":"large-language-models-as-tool-makers","title":"Large Language Models as Tool Makers","date":"2023-05-26","arxiv_id":"2305.17126","n_code_links":1,"syntology":null}],"record_sha256":"e09126effec071067a5fcdb4d9a7f19641c206f81a562042219b9ef5c0d46941","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}