{"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/16","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":16,"pages_in_order":20,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/method/gpt-3/papers/17","papers":[{"paper":null,"slug":"automated-interactive-domain-specific","title":"Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs","date":"2023-03-15","arxiv_id":"2303.08941","n_code_links":0,"syntology":null},{"paper":"/paper/selfcheckgpt-zero-resource-black-box","slug":"selfcheckgpt-zero-resource-black-box","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","date":"2023-03-15","arxiv_id":"2303.08896","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["potsawee/selfcheckgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","n_code_links":2,"syntology":null},{"paper":null,"slug":"re-move-an-adaptive-policy-design-approach","title":"RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback","date":"2023-03-14","arxiv_id":"2303.07622","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-the-workplace-a-case","title":"Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification","date":"2023-03-13","arxiv_id":"2303.07142","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-know-your-contextual","slug":"large-language-models-know-your-contextual","title":"Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search","date":"2023-03-12","arxiv_id":"2303.06573","n_code_links":2,"syntology":null},{"paper":"/paper/chatgpt-may-pass-the-bar-exam-soon-but-has-a","slug":"chatgpt-may-pass-the-bar-exam-soon-but-has-a","title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","date":"2023-03-09","arxiv_id":"2304.12202","n_code_links":1,"syntology":null},{"paper":"/paper/icl-d3ie-in-context-learning-with-diverse","slug":"icl-d3ie-in-context-learning-with-diverse","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","date":"2023-03-09","arxiv_id":"2303.05063","n_code_links":1,"syntology":null},{"paper":"/paper/chatgpt-participates-in-a-computer-science","slug":"chatgpt-participates-in-a-computer-science","title":"ChatGPT Participates in a Computer Science Exam","date":"2023-03-08","arxiv_id":"2303.09461","n_code_links":1,"syntology":null},{"paper":"/paper/cost-effective-hyperparameter-optimization","slug":"cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","date":"2023-03-08","arxiv_id":"2303.04673","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"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) · 3 unverified","official":{"repos":["microsoft/FLAML"],"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/on-the-risks-of-stealing-the-decoding","slug":"on-the-risks-of-stealing-the-decoding","title":"Stealing the Decoding Algorithms of Language Models","date":"2023-03-08","arxiv_id":"2303.04729","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-ai-generated","slug":"a-comprehensive-survey-of-ai-generated","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","date":"2023-03-07","arxiv_id":"2303.04226","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-generate-then-cache-cascade-of","slug":"prompt-generate-then-cache-cascade-of","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","date":"2023-03-03","arxiv_id":"2303.02151","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["zrrskywalker/cafo"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["milvlg/prophet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/wice-real-world-entailment-for-claims-in","slug":"wice-real-world-entailment-for-claims-in","title":"WiCE: Real-World Entailment for Claims in Wikipedia","date":"2023-03-02","arxiv_id":"2303.01432","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ryokamoi/wice"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-framework-to-generate-neurosymbolic-pddl","slug":"a-framework-to-generate-neurosymbolic-pddl","title":"A Framework for Neurosymbolic Robot Action Planning using Large Language Models","date":"2023-03-01","arxiv_id":"2303.00438","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":["alessiocpt/teriyaki"],"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":"how-robust-is-gpt-3-5-to-predecessors-a","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","date":"2023-03-01","arxiv_id":"2303.00293","n_code_links":0,"syntology":null},{"paper":null,"slug":"toxvis-enabling-interpretability-of-implicit","title":"ToxVis: Enabling Interpretability of Implicit vs. Explicit Toxicity Detection Models with Interactive Visualization","date":"2023-03-01","arxiv_id":"2303.09402","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-summarization-via-chatgpt","title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","date":"2023-02-28","arxiv_id":"2302.14229","n_code_links":0,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","n_code_links":57,"syntology":{"ran":37,"of":58,"n_ran_checked":25,"n_instrument":12,"unverified":21,"pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/reward-design-with-language-models","slug":"reward-design-with-language-models","title":"Reward Design with Language Models","date":"2023-02-27","arxiv_id":"2303.00001","n_code_links":1,"syntology":null},{"paper":"/paper/systematic-rectification-of-language-models","slug":"systematic-rectification-of-language-models","title":"Systematic Rectification of Language Models via Dead-end Analysis","date":"2023-02-27","arxiv_id":"2302.14003","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 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":["mcao516/rectification-lm"],"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":"comparing-sentence-level-suggestions-to","title":"Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication","date":"2023-02-26","arxiv_id":"2302.13382","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-attention-requires-bounded-entries","title":"Fast Attention Requires Bounded Entries","date":"2023-02-26","arxiv_id":"2302.13214","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-in-the-loop-schema-induction","title":"Human-in-the-Loop Schema Induction","date":"2023-02-25","arxiv_id":"2302.13048","n_code_links":0,"syntology":null},{"paper":null,"slug":"spanish-built-factual-freectianary-spanish","title":"Spanish Built Factual Freectianary (Spanish-BFF): the first AI-generated free dictionary","date":"2023-02-24","arxiv_id":"2302.12746","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-ai-performance-on-less-frequent","title":"Testing AI on language comprehension tasks reveals insensitivity to underlying meaning","date":"2023-02-23","arxiv_id":"2302.12313","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"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","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"]}}},{"paper":null,"slug":"k-nn-adapter-efficient-domain-adaptation-for","title":"$k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models","date":"2023-02-21","arxiv_id":"2302.10879","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-information-extraction-via-chatting","slug":"zero-shot-information-extraction-via-chatting","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","date":"2023-02-20","arxiv_id":"2302.10205","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-on-pretrained","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","date":"2023-02-18","arxiv_id":"2302.09419","n_code_links":0,"syntology":null},{"paper":"/paper/bounding-the-capabilities-of-large-language","slug":"bounding-the-capabilities-of-large-language","title":"Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints","date":"2023-02-17","arxiv_id":"2302.09185","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt4mia-utilizing-geneative-pre-trained","title":"GPT4MIA: Utilizing Generative Pre-trained Transformer (GPT-3) as A Plug-and-Play Transductive Model for Medical Image Analysis","date":"2023-02-17","arxiv_id":"2302.08722","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-large-language-models-with-the","title":"Prompting Large Language Models With the Socratic Method","date":"2023-02-17","arxiv_id":"2303.08769","n_code_links":0,"syntology":null},{"paper":"/paper/keep-it-neutral-using-natural-language","slug":"keep-it-neutral-using-natural-language","title":"For Generated Text, Is NLI-Neutral Text the Best Text?","date":"2023-02-16","arxiv_id":"2302.08577","n_code_links":1,"syntology":null},{"paper":"/paper/learning-performance-improving-code-edits","slug":"learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","n_code_links":2,"syntology":{"ran":8,"of":19,"n_ran_checked":3,"n_instrument":5,"unverified":11,"pointer_only":19,"phrase":"8 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; 5 where Syntology's instrument failed) · 11 unverified","official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/scattershot-interactive-in-context-example","slug":"scattershot-interactive-in-context-example","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","date":"2023-02-14","arxiv_id":"2302.07346","n_code_links":1,"syntology":null},{"paper":"/paper/can-gpt-3-perform-statutory-reasoning","slug":"can-gpt-3-perform-statutory-reasoning","title":"Can GPT-3 Perform Statutory Reasoning?","date":"2023-02-13","arxiv_id":"2302.06100","n_code_links":1,"syntology":null},{"paper":null,"slug":"street-a-multi-task-structured-reasoning-and","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","date":"2023-02-13","arxiv_id":"2302.06729","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-brief-report-on-lawgpt-1-0-a-virtual-legal","title":"A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3","date":"2023-02-11","arxiv_id":"2302.05729","n_code_links":0,"syntology":null},{"paper":null,"slug":"reliable-natural-language-understanding-with","title":"Reliable Natural Language Understanding with Large Language Models and Answer Set Programming","date":"2023-02-07","arxiv_id":"2302.03780","n_code_links":0,"syntology":null},{"paper":"/paper/what-matters-in-the-structured-pruning-of","slug":"what-matters-in-the-structured-pruning-of","title":"What Matters In The Structured Pruning of Generative Language Models?","date":"2023-02-07","arxiv_id":"2302.03773","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["huggingface/nn_pruning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"theory-of-mind-may-have-spontaneously-emerged","title":"Evaluating Large Language Models in Theory of Mind Tasks","date":"2023-02-04","arxiv_id":"2302.02083","n_code_links":0,"syntology":null},{"paper":null,"slug":"creating-a-large-language-model-of-a","title":"Creating a Large Language Model of a Philosopher","date":"2023-02-02","arxiv_id":"2302.01339","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-writing-with-opinionated-language-models","title":"Co-Writing with Opinionated Language Models Affects Users' Views","date":"2023-02-01","arxiv_id":"2302.00560","n_code_links":0,"syntology":null},{"paper":"/paper/improving-few-shot-generalization-by-1","slug":"improving-few-shot-generalization-by-1","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","date":"2023-02-01","arxiv_id":"2302.00674","n_code_links":1,"syntology":null},{"paper":null,"slug":"numeracy-from-literacy-data-science-as-an","title":"Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models","date":"2023-01-31","arxiv_id":"2301.13382","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-machine-translation-with-large","slug":"adaptive-machine-translation-with-large","title":"Adaptive Machine Translation with Large Language Models","date":"2023-01-30","arxiv_id":"2301.13294","n_code_links":1,"syntology":null},{"paper":"/paper/replug-retrieval-augmented-black-box-language","slug":"replug-retrieval-augmented-black-box-language","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","date":"2023-01-30","arxiv_id":"2301.12652","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/specializing-smaller-language-models-towards","slug":"specializing-smaller-language-models-towards","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","date":"2023-01-30","arxiv_id":"2301.12726","n_code_links":2,"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":["FranxYao/FlanT5-CoT-Specialization"],"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":null,"slug":"a-discerning-several-thousand-judgments-gpt-3","title":"A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction","date":"2023-01-29","arxiv_id":"2301.12564","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":2,"of":7,"n_ran_checked":2,"n_instrument":0,"unverified":5,"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","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"]}}},{"paper":null,"slug":"understanding-the-effectiveness-of-very-large","title":"Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation","date":"2023-01-27","arxiv_id":"2301.12004","n_code_links":0,"syntology":null},{"paper":"/paper/causal-reasoning-of-entities-and-events-in","slug":"causal-reasoning-of-entities-and-events-in","title":"Causal Reasoning of Entities and Events in Procedural Texts","date":"2023-01-26","arxiv_id":"2301.10896","n_code_links":1,"syntology":{"ran":7,"of":15,"n_ran_checked":7,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["zharry29/causal_reasoning_of_entities_and_events"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-very-large-pretrained-language-models","title":"The Next Chapter: A Study of Large Language Models in Storytelling","date":"2023-01-24","arxiv_id":"2301.09790","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-fiduciaries-a-case","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","date":"2023-01-24","arxiv_id":"2301.10095","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-can-segment-narrative","title":"Large language models can segment narrative events similarly to humans","date":"2023-01-24","arxiv_id":"2301.10297","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-instruction-based-prompting-for","title":"Multitask Instruction-based Prompting for Fallacy Recognition","date":"2023-01-24","arxiv_id":"2301.09992","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-model-gpt-3-dis-informs-us-better-than","title":"AI model GPT-3 (dis)informs us better than humans","date":"2023-01-23","arxiv_id":"2301.11924","n_code_links":0,"syntology":null},{"paper":null,"slug":"superscaler-supporting-flexible-dnn","title":"SuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction","date":"2023-01-21","arxiv_id":"2301.08984","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-good-translator-a-preliminary","slug":"is-chatgpt-a-good-translator-a-preliminary","title":"Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine","date":"2023-01-20","arxiv_id":"2301.08745","n_code_links":1,"syntology":null},{"paper":"/paper/batch-prompting-efficient-inference-with","slug":"batch-prompting-efficient-inference-with","title":"Batch Prompting: Efficient Inference with Large Language Model APIs","date":"2023-01-19","arxiv_id":"2301.08721","n_code_links":2,"syntology":null},{"paper":"/paper/gpt-as-knowledge-worker-a-zero-shot","slug":"gpt-as-knowledge-worker-a-zero-shot","title":"GPT as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA Capabilities","date":"2023-01-11","arxiv_id":"2301.04408","n_code_links":1,"syntology":null},{"paper":null,"slug":"recommending-root-cause-and-mitigation-steps","title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models","date":"2023-01-10","arxiv_id":"2301.03797","n_code_links":0,"syntology":null},{"paper":"/paper/critical-perspectives-a-benchmark-revealing","slug":"critical-perspectives-a-benchmark-revealing","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","date":"2023-01-05","arxiv_id":"2301.01874","n_code_links":1,"syntology":null},{"paper":"/paper/inpars-v2-large-language-models-as-efficient","slug":"inpars-v2-large-language-models-as-efficient","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","date":"2023-01-04","arxiv_id":"2301.01820","n_code_links":1,"syntology":null},{"paper":"/paper/unihd-at-tsar-2022-shared-task-is-compute-all","slug":"unihd-at-tsar-2022-shared-task-is-compute-all","title":"UniHD at TSAR-2022 Shared Task: Is Compute All We Need for Lexical Simplification?","date":"2023-01-04","arxiv_id":"2301.01764","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":"/paper/fusing-pre-trained-language-models-with","slug":"fusing-pre-trained-language-models-with","title":"Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"promptcap-prompt-guided-image-captioning-for","title":"PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeted-phishing-campaigns-using-large-scale","title":"Targeted Phishing Campaigns using Large Scale Language Models","date":"2022-12-30","arxiv_id":"2301.00665","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","n_code_links":5,"syntology":null},{"paper":null,"slug":"maximizing-use-case-specificity-through","title":"Maximizing Use-Case Specificity through Precision Model Tuning","date":"2022-12-29","arxiv_id":"2212.14206","n_code_links":0,"syntology":null},{"paper":"/paper/deepcuts-single-shot-interpretability-based","slug":"deepcuts-single-shot-interpretability-based","title":"DeepCuts: Single-Shot Interpretability based Pruning for BERT","date":"2022-12-27","arxiv_id":"2212.13392","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-generate","title":"Using Large Language Models to Generate Engaging Captions for Data Visualizations","date":"2022-12-27","arxiv_id":"2212.14047","n_code_links":0,"syntology":null},{"paper":null,"slug":"biologically-inspired-design-concept","title":"Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers","date":"2022-12-26","arxiv_id":"2212.13196","n_code_links":0,"syntology":null},{"paper":null,"slug":"jasmine-arabic-gpt-models-for-few-shot","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","date":"2022-12-21","arxiv_id":"2212.10755","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-text-generation-with-language","title":"Controllable Text Generation with Language Constraints","date":"2022-12-20","arxiv_id":"2212.10466","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-have-coherent-mental","slug":"do-language-models-have-coherent-mental","title":"Do language models have coherent mental models of everyday things?","date":"2022-12-20","arxiv_id":"2212.10029","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["allenai/everyday-things"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/docasref-a-pilot-empirical-study-on","slug":"docasref-a-pilot-empirical-study-on","title":"DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely","date":"2022-12-20","arxiv_id":"2212.10013","n_code_links":1,"syntology":null},{"paper":null,"slug":"generic-temporal-reasoning-with-differential","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","date":"2022-12-20","arxiv_id":"2212.10467","n_code_links":0,"syntology":null},{"paper":null,"slug":"go-tuning-improving-zero-shot-learning","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","date":"2022-12-20","arxiv_id":"2212.10461","n_code_links":0,"syntology":null},{"paper":"/paper/is-gpt-3-a-good-data-annotator","slug":"is-gpt-3-a-good-data-annotator","title":"Is GPT-3 a Good Data Annotator?","date":"2022-12-20","arxiv_id":"2212.10450","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-3-a-psychopath-evaluating-large","title":"Evaluating Psychological Safety of Large Language Models","date":"2022-12-20","arxiv_id":"2212.10529","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-reasoning-teachers","slug":"large-language-models-are-reasoning-teachers","title":"Large Language Models Are Reasoning Teachers","date":"2022-12-20","arxiv_id":"2212.10071","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itsnamgyu/reasoning-teacher"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pairreranker-pairwise-reranking-for-natural","title":"PairReranker: Pairwise Reranking for Natural Language Generation","date":"2022-12-20","arxiv_id":"2212.10555","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-your-tone-introducing-a-new","slug":"pay-attention-to-your-tone-introducing-a-new","title":"Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite","date":"2022-12-20","arxiv_id":"2212.10190","n_code_links":1,"syntology":null},{"paper":null,"slug":"true-detective-a-challenging-benchmark-for","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","date":"2022-12-20","arxiv_id":"2212.10114","n_code_links":0,"syntology":null},{"paper":"/paper/emergent-analogical-reasoning-in-large","slug":"emergent-analogical-reasoning-in-large","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","arxiv_id":"2212.09196","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":["taylorwwebb/emergent_analogies_llm"],"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-human-language-model-interaction","slug":"evaluating-human-language-model-interaction","title":"Evaluating Human-Language Model Interaction","date":"2022-12-19","arxiv_id":"2212.09746","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-reasoners-with-self","slug":"large-language-models-are-reasoners-with-self","title":"Large Language Models are Better Reasoners with Self-Verification","date":"2022-12-19","arxiv_id":"2212.09561","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["WENGSYX/Self-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/lens-a-learnable-evaluation-metric-for-text","slug":"lens-a-learnable-evaluation-metric-for-text","title":"LENS: A Learnable Evaluation Metric for Text Simplification","date":"2022-12-19","arxiv_id":"2212.09739","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","n_code_links":2,"syntology":null},{"paper":"/paper/can-retriever-augmented-language-models","slug":"can-retriever-augmented-language-models","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","date":"2022-12-18","arxiv_id":"2212.09146","n_code_links":1,"syntology":null},{"paper":"/paper/self-prompting-large-language-models-for-open","slug":"self-prompting-large-language-models-for-open","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","date":"2022-12-16","arxiv_id":"2212.08635","n_code_links":1,"syntology":null},{"paper":"/paper/revisiting-the-gold-standard-grounding","slug":"revisiting-the-gold-standard-grounding","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","date":"2022-12-15","arxiv_id":"2212.07981","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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":["yale-lily/rose"],"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":"/paper/crepe-can-vision-language-foundation-models","slug":"crepe-can-vision-language-foundation-models","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","date":"2022-12-13","arxiv_id":"2212.07796","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["raivnlab/crepe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"f1422b5466dc8dcb5bc5d458da579473ddf7fe2f6271686e812892d6c8e8d5cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}