{"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/gpt-3/papers/15","list_of":"/method/gpt-3","method":"GPT-3","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":15,"pages_in_order":20,"rows_per_page":100,"rows":[1401,1500],"of":1906,"counts":{"archive_papers_tagged":1906,"with_a_code_link":866,"where_syntology_ran_a_sample":319,"not_listed_spam_title":0,"listed":1906,"listed_where_code_ran":319,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":259,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":259,"listed_every_run_a_failure_of_syntologys_instrument":60,"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/gpt-3","prev":"/method/gpt-3/papers/14","next":"/method/gpt-3/papers/16","papers":[{"paper":null,"slug":"revisiting-relation-extraction-in-the-era-of","title":"Revisiting Relation Extraction in the era of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05003","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-don-t-always-say-what-they-1","slug":"language-models-don-t-always-say-what-they-1","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","date":"2023-05-07","arxiv_id":"2305.04388","n_code_links":2,"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":["milesaturpin/cot-unfaithfulness"],"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":"professional-certification-benchmark-dataset","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","date":"2023-05-07","arxiv_id":"2305.05377","n_code_links":0,"syntology":null},{"paper":"/paper/plan-and-solve-prompting-improving-zero-shot","slug":"plan-and-solve-prompting-improving-zero-shot","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","date":"2023-05-06","arxiv_id":"2305.04091","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["agi-edgerunners/plan-and-solve-prompting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","n_code_links":1,"syntology":null},{"paper":"/paper/otter-a-multi-modal-model-with-in-context","slug":"otter-a-multi-modal-model-with-in-context","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","date":"2023-05-05","arxiv_id":"2305.03726","n_code_links":1,"syntology":null},{"paper":"/paper/using-chatgpt-for-entity-matching","slug":"using-chatgpt-for-entity-matching","title":"Using ChatGPT for Entity Matching","date":"2023-05-05","arxiv_id":"2305.03423","n_code_links":1,"syntology":null},{"paper":"/paper/verify-and-edit-a-knowledge-enhanced-chain-of","slug":"verify-and-edit-a-knowledge-enhanced-chain-of","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","date":"2023-05-05","arxiv_id":"2305.03268","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-automatically-discovered-chain-of-thought","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","date":"2023-05-04","arxiv_id":"2305.02897","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-a-review-on-advancements-and","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","date":"2023-05-04","arxiv_id":"2305.03195","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-time-preferences-and-consumer","title":"Can LLMs Capture Human Preferences?","date":"2023-05-04","arxiv_id":"2305.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"late-binding-scholarship-in-the-age-of-ai","title":"Late-Binding Scholarship in the Age of AI: Navigating Legal and Normative Challenges of a New Form of Knowledge Production","date":"2023-05-04","arxiv_id":"2305.11058","n_code_links":0,"syntology":null},{"paper":"/paper/personallm-investigating-the-ability-of-gpt-3","slug":"personallm-investigating-the-ability-of-gpt-3","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","date":"2023-05-04","arxiv_id":"2305.02547","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":{"repos":["hjian42/personallm"],"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":["official"]}}},{"paper":"/paper/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":"/paper/gpt-re-in-context-learning-for-relation","slug":"gpt-re-in-context-learning-for-relation","title":"GPT-RE: In-context Learning for Relation Extraction using Large Language Models","date":"2023-05-03","arxiv_id":"2305.02105","n_code_links":1,"syntology":null},{"paper":"/paper/discern-and-answer-mitigating-the-impact-of","slug":"discern-and-answer-mitigating-the-impact-of","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","date":"2023-05-02","arxiv_id":"2305.01579","n_code_links":1,"syntology":null},{"paper":null,"slug":"freelm-fine-tuning-free-language-model","title":"FreeLM: Fine-Tuning-Free Language Model","date":"2023-05-02","arxiv_id":"2305.01616","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-unleash-the-power-of-large-language","slug":"how-to-unleash-the-power-of-large-language","title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","date":"2023-05-02","arxiv_id":"2305.01555","n_code_links":2,"syntology":null},{"paper":null,"slug":"new-trends-in-machine-translation-using-large","title":"A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models","date":"2023-05-02","arxiv_id":"2305.01181","n_code_links":0,"syntology":null},{"paper":"/paper/vision-meets-definitions-unsupervised-visual","slug":"vision-meets-definitions-unsupervised-visual","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","date":"2023-05-02","arxiv_id":"2305.01788","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-effectiveness-of-large-language","slug":"exploring-the-effectiveness-of-large-language","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","date":"2023-04-30","arxiv_id":"2305.00418","n_code_links":1,"syntology":null},{"paper":"/paper/causal-reasoning-and-large-language-models","slug":"causal-reasoning-and-large-language-models","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","date":"2023-04-28","arxiv_id":"2305.00050","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["py-why/pywhy-llm"],"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":"framing-the-news-from-human-perception-to","title":"Framing the News:From Human Perception to Large Language Model Inferences","date":"2023-04-27","arxiv_id":"2304.14456","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-state-of-the-art-1","slug":"large-language-models-are-state-of-the-art-1","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","date":"2023-04-27","arxiv_id":"2304.14317","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["terryyz/llm-code-eval","terryyz/ice-score"],"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"]}}},{"paper":null,"slug":"origin-tracing-and-detecting-of-llms","title":"Origin Tracing and Detecting of LLMs","date":"2023-04-27","arxiv_id":"2304.14072","n_code_links":0,"syntology":null},{"paper":"/paper/swectrl-mini-a-data-transparent-transformer","slug":"swectrl-mini-a-data-transparent-transformer","title":"SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish","date":"2023-04-27","arxiv_id":"2304.13994","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-based-reasoning-framework-for-adaptive","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","date":"2023-04-26","arxiv_id":"2304.13301","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-5-and-gpt-4-for","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","date":"2023-04-26","arxiv_id":"2304.13714","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-structured-seed-mediated-gold","title":"Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3","date":"2023-04-26","arxiv_id":"2304.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-multi-modal-dbmss-for-seamless","title":"Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables","date":"2023-04-26","arxiv_id":"2304.13559","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-massive-multitask-chinese","slug":"measuring-massive-multitask-chinese","title":"Measuring Massive Multitask Chinese Understanding","date":"2023-04-25","arxiv_id":"2304.12986","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Felixgithub2017/MMCU"],"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":["official","unlocated"]}}},{"paper":null,"slug":"semantic-compression-with-large-language","title":"Semantic Compression With Large Language Models","date":"2023-04-25","arxiv_id":"2304.12512","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-theory-of-mind-performance-in-large","slug":"boosting-theory-of-mind-performance-in-large","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","date":"2023-04-22","arxiv_id":"2304.11490","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-transformer-language-models-on-1","slug":"evaluating-transformer-language-models-on-1","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","date":"2023-04-21","arxiv_id":"2304.10977","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-anxiety-in-large-language-models","title":"Inducing anxiety in large language models can induce bias","date":"2023-04-21","arxiv_id":"2304.11111","n_code_links":0,"syntology":null},{"paper":null,"slug":"who-s-the-best-detective-llms-vs-mls-in","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","date":"2023-04-21","arxiv_id":"2304.11257","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-semantics-towards-better-natural","title":"Meta Semantics: Towards better natural language understanding and reasoning","date":"2023-04-20","arxiv_id":"2304.10663","n_code_links":0,"syntology":null},{"paper":null,"slug":"sinc-spatial-composition-of-3d-human-motions","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","date":"2023-04-20","arxiv_id":"2304.10417","n_code_links":0,"syntology":null},{"paper":null,"slug":"catch-me-if-you-can-identifying-fraudulent","title":"Catch Me If You Can: Identifying Fraudulent Physician Reviews with Large Language Models Using Generative Pre-Trained Transformers","date":"2023-04-19","arxiv_id":"2304.09948","n_code_links":0,"syntology":null},{"paper":"/paper/genegpt-teaching-large-language-models-to-use","slug":"genegpt-teaching-large-language-models-to-use","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","date":"2023-04-19","arxiv_id":"2304.09667","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":["ncbi/GeneGPT"],"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":null,"slug":"supporting-human-ai-collaboration-in-auditing","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","date":"2023-04-19","arxiv_id":"2304.09991","n_code_links":0,"syntology":null},{"paper":null,"slug":"cancergpt-few-shot-drug-pair-synergy","title":"CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models","date":"2023-04-18","arxiv_id":"2304.10946","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-interaction-for-content-generation","title":"LLM-based Interaction for Content Generation: A Case Study on the Perception of Employees in an IT department","date":"2023-04-18","arxiv_id":"2304.09064","n_code_links":0,"syntology":null},{"paper":"/paper/from-zero-to-hero-examining-the-power-of","slug":"from-zero-to-hero-examining-the-power-of","title":"From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.07995","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/symbolic-instruction-tuning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"supporting-qualitative-analysis-with-large","title":"Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding","date":"2023-04-17","arxiv_id":"2304.10548","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-program-repair-based-on-code-review","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","date":"2023-04-16","arxiv_id":"2304.07840","n_code_links":0,"syntology":null},{"paper":null,"slug":"sabia-portuguese-large-language-models","title":"Sabiá: Portuguese Large Language Models","date":"2023-04-16","arxiv_id":"2304.07880","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-instruction-following-language","slug":"towards-better-instruction-following-language","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","date":"2023-04-16","arxiv_id":"2304.07854","n_code_links":2,"syntology":null},{"paper":"/paper/api-bank-a-benchmark-for-tool-augmented-llms","slug":"api-bank-a-benchmark-for-tool-augmented-llms","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","date":"2023-04-14","arxiv_id":"2304.08244","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"chatgpt-applications-opportunities-and","title":"ChatGPT: Applications, Opportunities, and Threats","date":"2023-04-14","arxiv_id":"2304.09103","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-clip-know-about-a-red-circle-visual","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","date":"2023-04-13","arxiv_id":"2304.06712","n_code_links":0,"syntology":null},{"paper":"/paper/detection-of-fake-generated-scientific","slug":"detection-of-fake-generated-scientific","title":"Detection of Fake Generated Scientific Abstracts","date":"2023-04-12","arxiv_id":"2304.06148","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-chatgpt-model-for-vulnerability","title":"Evaluation of ChatGPT Model for Vulnerability Detection","date":"2023-04-12","arxiv_id":"2304.07232","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-optimization-of-catalysts-with-in","slug":"bayesian-optimization-of-catalysts-with-in","title":"Bayesian Optimization of Catalysis With In-Context Learning","date":"2023-04-11","arxiv_id":"2304.05341","n_code_links":2,"syntology":null},{"paper":null,"slug":"distinguishing-chatgpt-3-5-4-generated-and","title":"Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis","date":"2023-04-11","arxiv_id":"2304.05534","n_code_links":0,"syntology":null},{"paper":"/paper/multi-step-jailbreaking-privacy-attacks-on","slug":"multi-step-jailbreaking-privacy-attacks-on","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","date":"2023-04-11","arxiv_id":"2304.05197","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["hkust-knowcomp/llm-multistep-jailbreak"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automated-reading-passage-generation-with","title":"Automated Reading Passage Generation with OpenAI's Large Language Model","date":"2023-04-10","arxiv_id":"2304.04616","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-possibilities-of-ai-generated-text","title":"On the Possibilities of AI-Generated Text Detection","date":"2023-04-10","arxiv_id":"2304.04736","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-ready-for","slug":"are-large-language-models-ready-for","title":"Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding","date":"2023-04-09","arxiv_id":"2304.05368","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-crawler-find-out-if-chatgpt-really","title":"ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about","date":"2023-04-06","arxiv_id":"2304.03325","n_code_links":0,"syntology":null},{"paper":"/paper/making-ai-less-thirsty-uncovering-and","slug":"making-ai-less-thirsty-uncovering-and","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","date":"2023-04-06","arxiv_id":"2304.03271","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["ren-research/making-ai-less-thirsty"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-evaluations-of-chatgpt-and-emotion","slug":"on-the-evaluations-of-chatgpt-and-emotion","title":"Towards Interpretable Mental Health Analysis with Large Language Models","date":"2023-04-06","arxiv_id":"2304.03347","n_code_links":2,"syntology":null},{"paper":"/paper/zero-shot-next-item-recommendation-using","slug":"zero-shot-next-item-recommendation-using","title":"Zero-Shot Next-Item Recommendation using Large Pretrained Language Models","date":"2023-04-06","arxiv_id":"2304.03153","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":null}},{"paper":null,"slug":"behavioral-estimates-of-conceptual-structure","title":"Conceptual structure coheres in human cognition but not in large language models","date":"2023-04-05","arxiv_id":"2304.02754","n_code_links":0,"syntology":null},{"paper":"/paper/document-level-machine-translation-with-large","slug":"document-level-machine-translation-with-large","title":"Document-Level Machine Translation with Large Language Models","date":"2023-04-05","arxiv_id":"2304.02210","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-master-key-unlocking","title":"Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT","date":"2023-04-05","arxiv_id":"2304.02213","n_code_links":0,"syntology":null},{"paper":null,"slug":"blockwise-compression-of-transformer-based","title":"Blockwise Compression of Transformer-based Models without Retraining","date":"2023-04-04","arxiv_id":"2304.01483","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-to-gpt-3-5-hold-my-scalpel-a-look-at","title":"GPT-4 to GPT-3.5: 'Hold My Scalpel' -- A Look at the Competency of OpenAI's GPT on the Plastic Surgery In-Service Training Exam","date":"2023-04-04","arxiv_id":"2304.01503","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-chatgpt-a-highly-fluent-grammatical-error","title":"Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation","date":"2023-04-04","arxiv_id":"2304.01746","n_code_links":0,"syntology":null},{"paper":"/paper/llm-adapters-an-adapter-family-for-parameter","slug":"llm-adapters-an-adapter-family-for-parameter","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01933","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agi-edgerunners/llm-adapters"],"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":["official"]}}},{"paper":"/paper/refiner-reasoning-feedback-on-intermediate","slug":"refiner-reasoning-feedback-on-intermediate","title":"REFINER: Reasoning Feedback on Intermediate Representations","date":"2023-04-04","arxiv_id":"2304.01904","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["debjitpaul/refiner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","n_code_links":2,"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":["huashen218/llm-deepfake-human-study"],"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/llmmaps-a-visual-metaphor-for-stratified","slug":"llmmaps-a-visual-metaphor-for-stratified","title":"LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models","date":"2023-04-02","arxiv_id":"2304.00457","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-gpt-4-and-chatgpt-on-japanese","slug":"evaluating-gpt-4-and-chatgpt-on-japanese","title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations","date":"2023-03-31","arxiv_id":"2303.18027","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-large-language","title":"GPT-4 can pass the Korean National Licensing Examination for Korean Medicine Doctors","date":"2023-03-31","arxiv_id":"2303.17807","n_code_links":0,"syntology":null},{"paper":null,"slug":"humans-in-humans-out-on-gpt-converging-toward","title":"Humans in Humans Out: On GPT Converging Toward Common Sense in both Success and Failure","date":"2023-03-30","arxiv_id":"2303.17276","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesis-of-mathematical-programs-from","title":"Synthesis of Mathematical programs from Natural Language Specifications","date":"2023-03-30","arxiv_id":"2304.03287","n_code_links":0,"syntology":null},{"paper":null,"slug":"advances-in-apparent-conceptual-physics","title":"Advances in apparent conceptual physics reasoning in GPT-4","date":"2023-03-29","arxiv_id":"2303.17012","n_code_links":0,"syntology":null},{"paper":"/paper/annollm-making-large-language-models-to-be","slug":"annollm-making-large-language-models-to-be","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","date":"2023-03-29","arxiv_id":"2303.16854","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nlpcode/annollm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-gpt-3-5-and-gpt-4-models-on","slug":"evaluating-gpt-3-5-and-gpt-4-models-on","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","date":"2023-03-29","arxiv_id":"2303.17003","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["piresramon/gpt-4-enem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ten-quick-tips-for-harnessing-the-power-of","slug":"ten-quick-tips-for-harnessing-the-power-of","title":"Ten Quick Tips for Harnessing the Power of ChatGPT/GPT-4 in Computational Biology","date":"2023-03-29","arxiv_id":"2303.16429","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-clinical-entity-recognition-using","slug":"zero-shot-clinical-entity-recognition-using","title":"Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering","date":"2023-03-29","arxiv_id":"2303.16416","n_code_links":1,"syntology":null},{"paper":"/paper/explicit-planning-helps-language-models-in","slug":"explicit-planning-helps-language-models-in","title":"Explicit Planning Helps Language Models in Logical Reasoning","date":"2023-03-28","arxiv_id":"2303.15714","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cindermond/explicit-planning-for-reasoning","cindermond/leap"],"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":"on-codex-prompt-engineering-for-ocl","title":"On Codex Prompt Engineering for OCL Generation: An Empirical Study","date":"2023-03-28","arxiv_id":"2303.16244","n_code_links":0,"syntology":null},{"paper":"/paper/kpeval-towards-fine-grained-semantic-based","slug":"kpeval-towards-fine-grained-semantic-based","title":"KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation","date":"2023-03-27","arxiv_id":"2303.15422","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-gpt-3-s-performance-in","title":"Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction","date":"2023-03-25","arxiv_id":"2303.14342","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-assist-in-hazard","title":"Can Large Language Models assist in Hazard Analysis?","date":"2023-03-25","arxiv_id":"2303.15473","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-is-becoming-a-turing-machine-here-are","title":"GPT is becoming a Turing machine: Here are some ways to program it","date":"2023-03-25","arxiv_id":"2303.14310","n_code_links":0,"syntology":null},{"paper":"/paper/get-ready-for-a-party-exploring-smarter-smart","slug":"get-ready-for-a-party-exploring-smarter-smart","title":"\"Get ready for a party\": Exploring smarter smart spaces with help from large language models","date":"2023-03-24","arxiv_id":"2303.14143","n_code_links":1,"syntology":null},{"paper":null,"slug":"seal-semantic-frame-execution-and","title":"SEAL: Semantic Frame Execution And Localization for Perceiving Afforded Robot Actions","date":"2023-03-24","arxiv_id":"2303.14067","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-labeled-training-data-using-prompt","title":"Generate labeled training data using Prompt Programming and GPT-3. An example of Big Five Personality Classification","date":"2023-03-22","arxiv_id":"2303.12279","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-and-a-new-academic-reality-ai-written","title":"ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing","date":"2023-03-21","arxiv_id":"2303.13367","n_code_links":0,"syntology":null},{"paper":"/paper/ctbl-augmenting-large-language-models-for","slug":"ctbl-augmenting-large-language-models-for","title":"cTBLS: Augmenting Large Language Models with Conversational Tables","date":"2023-03-21","arxiv_id":"2303.12024","n_code_links":1,"syntology":null},{"paper":"/paper/sift-sparse-iso-flop-transformations-for","slug":"sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","arxiv_id":"2303.11525","n_code_links":2,"syntology":{"ran":21,"of":24,"n_ran_checked":20,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cerebrasresearch/sift","cerebrasresearch/sparse-ift"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/capabilities-of-gpt-4-on-medical-challenge","slug":"capabilities-of-gpt-4-on-medical-challenge","title":"Capabilities of GPT-4 on Medical Challenge Problems","date":"2023-03-20","arxiv_id":"2303.13375","n_code_links":1,"syntology":null},{"paper":null,"slug":"mind-meets-machine-unravelling-gpt-4-s","title":"Mind meets machine: Unravelling GPT-4's cognitive psychology","date":"2023-03-20","arxiv_id":"2303.11436","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-capability-analysis-of-gpt-3","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","date":"2023-03-18","arxiv_id":"2303.10420","n_code_links":0,"syntology":null},{"paper":null,"slug":"spdf-sparse-pre-training-and-dense-fine","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","date":"2023-03-18","arxiv_id":"2303.10464","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-wise-bit-compression-of-transformer","title":"Block-wise Bit-Compression of Transformer-based Models","date":"2023-03-16","arxiv_id":"2303.09184","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-the-scalable-evaluation-of","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","date":"2023-03-16","arxiv_id":"2303.13360","n_code_links":0,"syntology":null}],"record_sha256":"3b9e7e15c35c751c5e567890f27f0aa6d82229b989a0e9435fff08ff08b34311","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}