{"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/17","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":17,"pages_in_order":20,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/method/gpt-3/papers/18","papers":[{"paper":null,"slug":"paraphrase-identification-with-deep-learning","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","date":"2022-12-13","arxiv_id":"2212.06933","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-intuition-uncovering-human-like","title":"Thinking Fast and Slow in Large Language Models","date":"2022-12-10","arxiv_id":"2212.05206","n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-information-extraction-from","title":"Structured information extraction from complex scientific text with fine-tuned large language models","date":"2022-12-10","arxiv_id":"2212.05238","n_code_links":0,"syntology":null},{"paper":"/paper/llm-planner-few-shot-grounded-planning-for","slug":"llm-planner-few-shot-grounded-planning-for","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","date":"2022-12-08","arxiv_id":"2212.04088","n_code_links":1,"syntology":null},{"paper":"/paper/np4g-network-programming-for-generalization","slug":"np4g-network-programming-for-generalization","title":"NP4G : Network Programming for Generalization","date":"2022-12-08","arxiv_id":"2212.11118","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-role-of-ai-in-drug-discovery-challenges","title":"The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies","date":"2022-12-08","arxiv_id":"2212.08104","n_code_links":0,"syntology":null},{"paper":"/paper/deepspeed-data-efficiency-improving-deep","slug":"deepspeed-data-efficiency-improving-deep","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","date":"2022-12-07","arxiv_id":"2212.03597","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-testing-of-computer-vision-models","slug":"adaptive-testing-of-computer-vision-models","title":"Adaptive Testing of Computer Vision Models","date":"2022-12-06","arxiv_id":"2212.02774","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["i-gao/adavision"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/counterfactual-reasoning-do-language-models","slug":"counterfactual-reasoning-do-language-models","title":"Counterfactual reasoning: Do language models need world knowledge for causal understanding?","date":"2022-12-06","arxiv_id":"2212.03278","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-differentially","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","date":"2022-12-03","arxiv_id":"2212.01539","n_code_links":0,"syntology":null},{"paper":"/paper/sumren-summarizing-reported-speech-about","slug":"sumren-summarizing-reported-speech-about","title":"SumREN: Summarizing Reported Speech about Events in News","date":"2022-12-02","arxiv_id":"2212.01146","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-gpt-3","title":"a survey on GPT-3","date":"2022-12-01","arxiv_id":"2212.00857","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-multi-step-reasoning-capabilities","slug":"distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-opinion-summarization-with-gpt-3","slug":"zero-shot-opinion-summarization-with-gpt-3","title":"Prompted Opinion Summarization with GPT-3.5","date":"2022-11-29","arxiv_id":"2211.15914","n_code_links":1,"syntology":null},{"paper":"/paper/gpt-neo-for-commonsense-reasoning-a","slug":"gpt-neo-for-commonsense-reasoning-a","title":"GPT-Neo for commonsense reasoning -- a theoretical and practical lens","date":"2022-11-28","arxiv_id":"2211.15593","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-bloom-an-empirical-study-on","title":"Understanding BLOOM: An empirical study on diverse NLP tasks","date":"2022-11-27","arxiv_id":"2211.14865","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-3-driven-pedagogical-agents-for-training","title":"GPT-3-driven pedagogical agents for training children's curious question-asking skills","date":"2022-11-25","arxiv_id":"2211.14228","n_code_links":0,"syntology":null},{"paper":"/paper/prompttts-controllable-text-to-speech-with","slug":"prompttts-controllable-text-to-speech-with","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","date":"2022-11-22","arxiv_id":"2211.12171","n_code_links":1,"syntology":null},{"paper":"/paper/language-in-a-bottle-language-model-guided","slug":"language-in-a-bottle-language-model-guided","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","date":"2022-11-21","arxiv_id":"2211.11158","n_code_links":2,"syntology":null},{"paper":"/paper/ignore-previous-prompt-attack-techniques-for","slug":"ignore-previous-prompt-attack-techniques-for","title":"Ignore Previous Prompt: Attack Techniques For Language Models","date":"2022-11-17","arxiv_id":"2211.09527","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["agencyenterprise/promptinject"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/unisumm-unified-few-shot-summarization-with","slug":"unisumm-unified-few-shot-summarization-with","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","date":"2022-11-17","arxiv_id":"2211.09783","n_code_links":1,"syntology":null},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/glue-x-evaluating-natural-language","slug":"glue-x-evaluating-natural-language","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","date":"2022-11-15","arxiv_id":"2211.08073","n_code_links":1,"syntology":null},{"paper":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","n_code_links":1,"syntology":null},{"paper":null,"slug":"robbert-2022-updating-a-dutch-language-model","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","date":"2022-11-15","arxiv_id":"2211.08192","n_code_links":0,"syntology":null},{"paper":"/paper/are-hard-examples-also-harder-to-explain-a","slug":"are-hard-examples-also-harder-to-explain-a","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","date":"2022-11-14","arxiv_id":"2211.07517","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swarnahub/explanationhardness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ugif-ui-grounded-instruction-following","slug":"ugif-ui-grounded-instruction-following","title":"UGIF: UI Grounded Instruction Following","date":"2022-11-14","arxiv_id":"2211.07615","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-optimizing-the-communication-of-model","title":"On Optimizing the Communication of Model Parallelism","date":"2022-11-10","arxiv_id":"2211.05322","n_code_links":0,"syntology":null},{"paper":"/paper/active-example-selection-for-in-context","slug":"active-example-selection-for-in-context","title":"Active Example Selection for In-Context Learning","date":"2022-11-08","arxiv_id":"2211.04486","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":4,"n_instrument":6,"unverified":6,"pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["chicagohai/active-example-selection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"using-large-pre-trained-language-model-to","title":"Using Large Pre-Trained Language Model to Assist FDA in Premarket Medical Device","date":"2022-11-03","arxiv_id":"2212.01217","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-zero-shot-and-few-shot-table-question","title":"Towards Zero-Shot and Few-Shot Table Question Answering using GPT-3","date":"2022-10-31","arxiv_id":"2210.17284","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-decompose-hypothetical-question","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","date":"2022-10-30","arxiv_id":"2210.16865","n_code_links":0,"syntology":null},{"paper":"/paper/coco-dr-combating-distribution-shifts-in-zero","slug":"coco-dr-combating-distribution-shifts-in-zero","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","date":"2022-10-27","arxiv_id":"2210.15212","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["openmatch/coco-dr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"xricl-cross-lingual-retrieval-augmented-in","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","date":"2022-10-25","arxiv_id":"2210.13693","n_code_links":0,"syntology":null},{"paper":"/paper/abductive-action-inference","slug":"abductive-action-inference","title":"Inferring Past Human Actions in Homes with Abductive Reasoning","date":"2022-10-24","arxiv_id":"2210.13984","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-euphemism-detection-in-few-shot-and","slug":"exploring-euphemism-detection-in-few-shot-and","title":"Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings","date":"2022-10-24","arxiv_id":"2210.12926","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-large-language-models-for-multiple","slug":"leveraging-large-language-models-for-multiple","title":"Leveraging Large Language Models for Multiple Choice Question Answering","date":"2022-10-22","arxiv_id":"2210.12353","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["byu-pccl/leveraging-llms-for-mcqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wikiwhy-answering-and-explaining-cause-and","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","date":"2022-10-21","arxiv_id":"2210.12152","n_code_links":0,"syntology":null},{"paper":null,"slug":"3dall-e-integrating-text-to-image-ai-in-3d","title":"3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows","date":"2022-10-20","arxiv_id":"2210.11603","n_code_links":0,"syntology":null},{"paper":"/paper/composing-ensembles-of-pre-trained-models-via","slug":"composing-ensembles-of-pre-trained-models-via","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","date":"2022-10-20","arxiv_id":"2210.11522","n_code_links":0,"syntology":null},{"paper":null,"slug":"systematicity-in-gpt-3-s-interpretation-of","title":"Systematicity in GPT-3's Interpretation of Novel English Noun Compounds","date":"2022-10-18","arxiv_id":"2210.09492","n_code_links":0,"syntology":null},{"paper":null,"slug":"tiny-attention-adapter-contexts-are-more","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","date":"2022-10-18","arxiv_id":"2211.01979","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-gpt-3-to-be-reliable","slug":"prompting-gpt-3-to-be-reliable","title":"Prompting GPT-3 To Be Reliable","date":"2022-10-17","arxiv_id":"2210.09150","n_code_links":1,"syntology":null},{"paper":"/paper/normsage-multi-lingual-multi-cultural-norm","slug":"normsage-multi-lingual-multi-cultural-norm","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","date":"2022-10-16","arxiv_id":"2210.08604","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-cultural-commonsense-knowledge-at","slug":"extracting-cultural-commonsense-knowledge-at","title":"Extracting Cultural Commonsense Knowledge at Scale","date":"2022-10-14","arxiv_id":"2210.07763","n_code_links":2,"syntology":null},{"paper":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","n_code_links":1,"syntology":null},{"paper":"/paper/testaug-a-framework-for-augmenting-capability-1","slug":"testaug-a-framework-for-augmenting-capability-1","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","date":"2022-10-14","arxiv_id":"2210.08097","n_code_links":1,"syntology":null},{"paper":"/paper/constructing-natural-language-explanations","slug":"constructing-natural-language-explanations","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","date":"2022-10-13","arxiv_id":"2210.07222","n_code_links":1,"syntology":null},{"paper":null,"slug":"explanations-from-large-language-models-make","title":"Explanations from Large Language Models Make Small Reasoners Better","date":"2022-10-13","arxiv_id":"2210.06726","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-of-code-are-few-shot","slug":"language-models-of-code-are-few-shot","title":"Language Models of Code are Few-Shot Commonsense Learners","date":"2022-10-13","arxiv_id":"2210.07128","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["madaan/cocogen"],"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/large-language-models-are-few-1-shot-table","slug":"large-language-models-are-few-1-shot-table","title":"Large Language Models are few(1)-shot Table Reasoners","date":"2022-10-13","arxiv_id":"2210.06710","n_code_links":1,"syntology":null},{"paper":null,"slug":"are-sample-efficient-nlp-models-more-robust","title":"Are Sample-Efficient NLP Models More Robust?","date":"2022-10-12","arxiv_id":"2210.06456","n_code_links":0,"syntology":null},{"paper":"/paper/rev-information-theoretic-evaluation-of-free","slug":"rev-information-theoretic-evaluation-of-free","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","date":"2022-10-10","arxiv_id":"2210.04982","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["hanjiechen/rev"],"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":"the-minimum-wage-as-an-anchor-effects-on","title":"The Minimum Wage as an Anchor: Effects on Determinations of Fairness by Humans and AI","date":"2022-10-10","arxiv_id":"2210.10585","n_code_links":0,"syntology":null},{"paper":"/paper/asdot-any-shot-data-to-text-generation-with","slug":"asdot-any-shot-data-to-text-generation-with","title":"ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models","date":"2022-10-09","arxiv_id":"2210.04325","n_code_links":1,"syntology":null},{"paper":"/paper/controllable-dialogue-simulation-with-in","slug":"controllable-dialogue-simulation-with-in","title":"Controllable Dialogue Simulation with In-Context Learning","date":"2022-10-09","arxiv_id":"2210.04185","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-chain-of-thought-prompting-in-large","slug":"automatic-chain-of-thought-prompting-in-large","title":"Automatic Chain of Thought Prompting in Large Language Models","date":"2022-10-07","arxiv_id":"2210.03493","n_code_links":5,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amazon-science/auto-cot"],"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":["named_in_paper"]}}},{"paper":"/paper/how-large-language-models-are-transforming","slug":"how-large-language-models-are-transforming","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","date":"2022-10-07","arxiv_id":"2210.03568","n_code_links":3,"syntology":null},{"paper":"/paper/measuring-and-narrowing-the-compositionality","slug":"measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","arxiv_id":"2210.03350","n_code_links":1,"syntology":null},{"paper":"/paper/binding-language-models-in-symbolic-languages","slug":"binding-language-models-in-symbolic-languages","title":"Binding Language Models in Symbolic Languages","date":"2022-10-06","arxiv_id":"2210.02875","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkunlp/binder"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"generalization-properties-of-retrieval-based","title":"Generalization Properties of Retrieval-based Models","date":"2022-10-06","arxiv_id":"2210.02617","n_code_links":0,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","n_code_links":1,"syntology":null},{"paper":"/paper/rainier-reinforced-knowledge-introspector-for","slug":"rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","arxiv_id":"2210.03078","n_code_links":1,"syntology":{"ran":7,"of":13,"n_ran_checked":4,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["liujch1998/rainier"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","n_code_links":9,"syntology":{"ran":15,"of":21,"n_ran_checked":14,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/explaining-patterns-in-data-with-language","slug":"explaining-patterns-in-data-with-language","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","date":"2022-10-04","arxiv_id":"2210.01848","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":["csinva/imodelsX"],"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":"complexity-based-prompting-for-multi-step","title":"Complexity-Based Prompting for Multi-Step Reasoning","date":"2022-10-03","arxiv_id":"2210.00720","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-greedy-reasoners-a","slug":"language-models-are-greedy-reasoners-a","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","date":"2022-10-03","arxiv_id":"2210.01240","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["asaparov/prontoqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-prompt-learning-via-policy-gradient","slug":"dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","arxiv_id":"2209.14610","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"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) · 4 unverified","official":null}},{"paper":null,"slug":"medical-image-captioning-via-generative","title":"Medical Image Captioning via Generative Pretrained Transformers","date":"2022-09-28","arxiv_id":"2209.13983","n_code_links":0,"syntology":null},{"paper":"/paper/who-is-gpt-3-an-exploration-of-personality","slug":"who-is-gpt-3-an-exploration-of-personality","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","date":"2022-09-28","arxiv_id":"2209.14338","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-critical-appraisal-of-equity-in","title":"How GPT-3 responds to different publics on climate change and Black Lives Matter: A critical appraisal of equity in conversational AI","date":"2022-09-27","arxiv_id":"2209.13627","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-ever-larger-octopi-still-amplify-reporting","title":"Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour","date":"2022-09-26","arxiv_id":"2209.12786","n_code_links":0,"syntology":null},{"paper":"/paper/news-summarization-and-evaluation-in-the-era","slug":"news-summarization-and-evaluation-in-the-era","title":"News Summarization and Evaluation in the Era of GPT-3","date":"2022-09-26","arxiv_id":"2209.12356","n_code_links":1,"syntology":null},{"paper":null,"slug":"moral-mimicry-large-language-models-produce","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","date":"2022-09-24","arxiv_id":"2209.12106","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-case-report-on-the-a-i-locked-in-problem","title":"A Case Report On The \"A.I. Locked-In Problem\": social concerns with modern NLP","date":"2022-09-22","arxiv_id":"2209.12687","n_code_links":0,"syntology":null},{"paper":"/paper/learn-to-explain-multimodal-reasoning-via","slug":"learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","arxiv_id":"2209.09513","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":0,"n_instrument":4,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["lupantech/ScienceQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/meta-adapters-parameter-efficient-few-shot","slug":"meta-adapters-parameter-efficient-few-shot","title":"Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning","date":"2022-09-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"will-it-blend-mixing-training-paradigms","title":"Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction","date":"2022-09-19","arxiv_id":"2209.08966","n_code_links":0,"syntology":null},{"paper":"/paper/psychologically-informed-chain-of-thought","slug":"psychologically-informed-chain-of-thought","title":"Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models","date":"2022-09-16","arxiv_id":"2209.08141","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["benpry/chain-of-thought-metaphor"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-and-patterns-for-effective-chain-of","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","date":"2022-09-16","arxiv_id":"2209.07686","n_code_links":0,"syntology":null},{"paper":null,"slug":"out-of-one-many-using-language-models-to","title":"Out of One, Many: Using Language Models to Simulate Human Samples","date":"2022-09-14","arxiv_id":"2209.06899","n_code_links":0,"syntology":null},{"paper":"/paper/chemberta-2-towards-chemical-foundation","slug":"chemberta-2-towards-chemical-foundation","title":"ChemBERTa-2: Towards Chemical Foundation Models","date":"2022-09-05","arxiv_id":"2209.01712","n_code_links":2,"syntology":null},{"paper":null,"slug":"evaluating-the-susceptibility-of-pre-trained","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","date":"2022-09-05","arxiv_id":"2209.02128","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-humans","slug":"do-large-language-models-know-what-humans","title":"Do Large Language Models know what humans know?","date":"2022-09-04","arxiv_id":"2209.01515","n_code_links":1,"syntology":null},{"paper":"/paper/elaboration-generating-commonsense-question","slug":"elaboration-generating-commonsense-question","title":"Elaboration-Generating Commonsense Question Answering at Scale","date":"2022-09-02","arxiv_id":"2209.01232","n_code_links":1,"syntology":null},{"paper":"/paper/folio-natural-language-reasoning-with-first","slug":"folio-natural-language-reasoning-with-first","title":"FOLIO: Natural Language Reasoning with First-Order Logic","date":"2022-09-02","arxiv_id":"2209.00840","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-reality-and-the-limits-of-language-data","title":"On Reality and the Limits of Language Data: Aligning LLMs with Human Norms","date":"2022-08-25","arxiv_id":"2208.11981","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mulzdg-multilingual-code-switching-framework","slug":"mulzdg-multilingual-code-switching-framework","title":"MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation","date":"2022-08-18","arxiv_id":"2208.08629","n_code_links":1,"syntology":null},{"paper":"/paper/using-large-language-models-to-simulate","slug":"using-large-language-models-to-simulate","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","date":"2022-08-18","arxiv_id":"2208.10264","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["gatiaher/using-large-language-models-to-replicate-human-subject-studies"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"targeted-honeyword-generation-with-language","title":"Targeted Honeyword Generation with Language Models","date":"2022-08-15","arxiv_id":"2208.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacher-guided-training-an-efficient","title":"Teacher Guided Training: An Efficient Framework for Knowledge Transfer","date":"2022-08-14","arxiv_id":"2208.06825","n_code_links":0,"syntology":null},{"paper":null,"slug":"debiased-large-language-models-still","title":"Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts","date":"2022-08-08","arxiv_id":"2208.04417","n_code_links":0,"syntology":null},{"paper":"/paper/what-can-transformers-learn-in-context-a-case","slug":"what-can-transformers-learn-in-context-a-case","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","date":"2022-08-01","arxiv_id":"2208.01066","n_code_links":2,"syntology":null},{"paper":null,"slug":"lad-language-models-as-data-for-zero-shot","title":"LAD: Language Models as Data for Zero-Shot Dialog","date":"2022-07-28","arxiv_id":"2207.14393","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-the-reverse-turing","title":"Large Language Models and the Reverse Turing Test","date":"2022-07-28","arxiv_id":"2207.14382","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-3-all-you-need-for-visual-question","title":"Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?","date":"2022-07-25","arxiv_id":"2207.12101","n_code_links":0,"syntology":null},{"paper":null,"slug":"bigissue-a-realistic-bug-localization","title":"BigIssue: A Realistic Bug Localization Benchmark","date":"2022-07-21","arxiv_id":"2207.10739","n_code_links":0,"syntology":null}],"record_sha256":"a756f90877ec3ef29a63f02f7a926493a902f4ece95e746b7277fffdbf491b33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}