{"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/19","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":19,"pages_in_order":20,"rows_per_page":100,"rows":[1801,1900],"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/18","next":"/method/gpt-3/papers/20","papers":[{"paper":null,"slug":"gaudi-conversational-interactions-with-deep","title":"Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections","date":"2021-12-05","arxiv_id":"2112.04404","n_code_links":0,"syntology":null},{"paper":null,"slug":"searching-for-efficient-transformers-for","title":"Searching for Efficient Transformers for Language Modeling","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tuning-large-neural-networks-via-zero-shot","slug":"tuning-large-neural-networks-via-zero-shot","title":"Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/amortized-prompt-lightweight-fine-tuning-for","slug":"amortized-prompt-lightweight-fine-tuning-for","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","date":"2021-11-25","arxiv_id":"2111.12853","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":8,"n_instrument":4,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["shogi880/DPLCLIP"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"active-dialogue-simulation-in-conversational","title":"Active Dialogue Simulation in Conversational Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-for-intent-classification","title":"Data Augmentation for Intent Classification with Generic Large Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eliteplm-an-empirical-study-on-general","title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-design","title":"Generative Pre-Trained Transformer for Design Concept Generation: An Exploration","date":"2021-11-16","arxiv_id":"2111.08489","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-gpt-3-after-deployment-with-a","title":"Improving GPT-3 after deployment with a dynamic memory of feedback","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-multilingual-capabilities-of-very-1","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource-1","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-coding-social-science-datasets-with","title":"Towards Coding Social Science Datasets with Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-law-for-recommendation-models-towards","title":"Scaling Law for Recommendation Models: Towards General-purpose User Representations","date":"2021-11-15","arxiv_id":"2111.11294","n_code_links":0,"syntology":null},{"paper":null,"slug":"amazon-sagemaker-model-parallelism-a-general","title":"Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training","date":"2021-11-10","arxiv_id":"2111.05972","n_code_links":0,"syntology":null},{"paper":"/paper/an-explanation-of-in-context-learning-as-1","slug":"an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","arxiv_id":"2111.02080","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/incontext-learning"],"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":null,"slug":"theeyecorpus-experiments-in-reducing-nlp-bias","title":"TheEyeCorpus: Experiments in Reducing NLP Bias and Identifiability for Large LMs","date":"2021-11-03","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"risks-of-ai-foundation-models-in-education","title":"Risks of AI Foundation Models in Education","date":"2021-10-19","arxiv_id":"2110.10024","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-inheritance-for-pre-trained-1","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-improves","title":"Sharpness-Aware Minimization Improves Language Model Generalization","date":"2021-10-16","arxiv_id":"2110.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-10-16","arxiv_id":"2110.08525","n_code_links":0,"syntology":null},{"paper":"/paper/delphi-towards-machine-ethics-and-norms","slug":"delphi-towards-machine-ethics-and-norms","title":"Can Machines Learn Morality? The Delphi Experiment","date":"2021-10-14","arxiv_id":"2110.07574","n_code_links":1,"syntology":null},{"paper":"/paper/symbolic-knowledge-distillation-from-general","slug":"symbolic-knowledge-distillation-from-general","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","date":"2021-10-14","arxiv_id":"2110.07178","n_code_links":1,"syntology":null},{"paper":null,"slug":"scaling-laws-for-the-few-shot-adaptation-of-1","title":"Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers","date":"2021-10-13","arxiv_id":"2110.06990","n_code_links":0,"syntology":null},{"paper":"/paper/list-lite-self-training-makes-efficient-few-1","slug":"list-lite-self-training-makes-efficient-few-1","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","date":"2021-10-12","arxiv_id":"2110.06274","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/list"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/yuan-1-0-large-scale-pre-trained-language","slug":"yuan-1-0-large-scale-pre-trained-language","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","date":"2021-10-10","arxiv_id":"2110.04725","n_code_links":1,"syntology":null},{"paper":null,"slug":"m6-10t-a-sharing-delinking-paradigm-for","title":"M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining","date":"2021-10-08","arxiv_id":"2110.03888","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-the-inductive-bias-of-large","title":"Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning","date":"2021-10-05","arxiv_id":"2110.02370","n_code_links":0,"syntology":null},{"paper":null,"slug":"collaborative-storytelling-with-human-actors","title":"Collaborative Storytelling with Human Actors and AI Narrators","date":"2021-09-29","arxiv_id":"2109.14728","n_code_links":0,"syntology":null},{"paper":"/paper/raft-a-real-world-few-shot-text","slug":"raft-a-real-world-few-shot-text","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","date":"2021-09-28","arxiv_id":"2109.14076","n_code_links":1,"syntology":null},{"paper":"/paper/turingbench-a-benchmark-environment-for","slug":"turingbench-a-benchmark-environment-for","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","date":"2021-09-27","arxiv_id":"2109.13296","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":null,"slug":"recursively-summarizing-books-with-human","title":"Recursively Summarizing Books with Human Feedback","date":"2021-09-22","arxiv_id":"2109.10862","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-zero-label-language-learning","title":"Towards Zero-Label Language Learning","date":"2021-09-19","arxiv_id":"2109.09193","n_code_links":0,"syntology":null},{"paper":"/paper/primer-searching-for-efficient-transformers","slug":"primer-searching-for-efficient-transformers","title":"Primer: Searching for Efficient Transformers for Language Modeling","date":"2021-09-17","arxiv_id":"2109.08668","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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/an-empirical-study-of-gpt-3-for-few-shot","slug":"an-empirical-study-of-gpt-3-for-few-shot","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","date":"2021-09-10","arxiv_id":"2109.05014","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":["microsoft/PICa"],"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/what-changes-can-large-scale-language-models","slug":"what-changes-can-large-scale-language-models","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","date":"2021-09-10","arxiv_id":"2109.04650","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":null}},{"paper":null,"slug":"medically-aware-gpt-3-as-a-data-generator-for","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","date":"2021-09-09","arxiv_id":"2110.07356","n_code_links":0,"syntology":null},{"paper":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","n_code_links":3,"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":["sylinrl/truthfulqa"],"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/general-purpose-question-answering-with-macaw","slug":"general-purpose-question-answering-with-macaw","title":"General-Purpose Question-Answering with Macaw","date":"2021-09-06","arxiv_id":"2109.02593","n_code_links":2,"syntology":null},{"paper":"/paper/gpt-3-models-are-poor-few-shot-learners-in","slug":"gpt-3-models-are-poor-few-shot-learners-in","title":"GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain","date":"2021-09-06","arxiv_id":"2109.02555","n_code_links":1,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","n_code_links":8,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"so-cloze-yet-so-far-n400-amplitude-is-better","title":"So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements","date":"2021-09-02","arxiv_id":"2109.01226","n_code_links":0,"syntology":null},{"paper":"/paper/minif2f-a-cross-system-benchmark-for-formal","slug":"minif2f-a-cross-system-benchmark-for-formal","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","date":"2021-08-31","arxiv_id":"2109.00110","n_code_links":4,"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":["openai/minif2f"],"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-multilingual-capabilities-of-very","slug":"on-the-multilingual-capabilities-of-very","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-08-30","arxiv_id":"2108.13349","n_code_links":2,"syntology":null},{"paper":"/paper/want-to-reduce-labeling-cost-gpt-3-can-help","slug":"want-to-reduce-labeling-cost-gpt-3-can-help","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","date":"2021-08-30","arxiv_id":"2108.13487","n_code_links":1,"syntology":null},{"paper":null,"slug":"cgems-a-metric-model-for-automatic-code","title":"CGEMs: A Metric Model for Automatic Code Generation using GPT-3","date":"2021-08-23","arxiv_id":"2108.10168","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-offset-block-embedding-array-robe-for","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","date":"2021-08-04","arxiv_id":"2108.02191","n_code_links":0,"syntology":null},{"paper":"/paper/q-pain-a-question-answering-dataset-to","slug":"q-pain-a-question-answering-dataset-to","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","date":"2021-08-03","arxiv_id":"2108.01764","n_code_links":0,"syntology":null},{"paper":"/paper/bertac-enhancing-transformer-based-language","slug":"bertac-enhancing-transformer-based-language","title":"BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"kuileixi-a-chinese-open-ended-text-adventure","title":"KuiLeiXi: a Chinese Open-Ended Text Adventure Game","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":null,"slug":"not-quite-ask-a-librarian-ai-on-the-nature","title":"Not Quite 'Ask a Librarian': AI on the Nature, Value, and Future of LIS","date":"2021-07-07","arxiv_id":"2107.05383","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","n_code_links":2,"syntology":null},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-a-measurement-using-gpt-3-on","title":"What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval","date":"2021-06-28","arxiv_id":"2106.14720","n_code_links":0,"syntology":null},{"paper":null,"slug":"process-for-adapting-language-models-to","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","date":"2021-06-18","arxiv_id":"2106.10328","n_code_links":0,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"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/gpt3-to-plan-extracting-plans-from-text-using","slug":"gpt3-to-plan-extracting-plans-from-text-using","title":"GPT3-to-plan: Extracting plans from text using GPT-3","date":"2021-06-14","arxiv_id":"2106.07131","n_code_links":1,"syntology":null},{"paper":"/paper/programming-puzzles","slug":"programming-puzzles","title":"Programming Puzzles","date":"2021-06-10","arxiv_id":"2106.05784","n_code_links":3,"syntology":null},{"paper":"/paper/timedial-temporal-commonsense-reasoning-in","slug":"timedial-temporal-commonsense-reasoning-in","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","date":"2021-06-08","arxiv_id":"2106.04571","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-perdetry-test-generating-new-meanings-for","title":"GPT Perdetry Test: Generating new meanings for new words","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-inheritance-for-pre-trained","slug":"knowledge-inheritance-for-pre-trained","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-05-28","arxiv_id":"2105.13880","n_code_links":2,"syntology":null},{"paper":"/paper/joint-retrieval-and-generation-training-for","slug":"joint-retrieval-and-generation-training-for","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","date":"2021-05-14","arxiv_id":"2105.06597","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-fly-controlled-text-generation-with","slug":"on-the-fly-controlled-text-generation-with","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","date":"2021-05-07","arxiv_id":"2105.03023","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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":["alisawuffles/DExperts"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"one-model-to-rule-them-all-towards-zero-shot","title":"One Model to Rule them All: Towards Zero-Shot Learning for Databases","date":"2021-05-03","arxiv_id":"2105.00642","n_code_links":0,"syntology":null},{"paper":"/paper/unreasonable-effectiveness-of-rule-based","slug":"unreasonable-effectiveness-of-rule-based","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","date":"2021-05-03","arxiv_id":"2105.01192","n_code_links":0,"syntology":null},{"paper":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/pangu-a-large-scale-autoregressive-pretrained","slug":"pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","n_code_links":5,"syntology":null},{"paper":"/paper/a-token-level-reference-free-hallucination","slug":"a-token-level-reference-free-hallucination","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","date":"2021-04-18","arxiv_id":"2104.08704","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":["microsoft/HaDes"],"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/fantastically-ordered-prompts-and-where-to","slug":"fantastically-ordered-prompts-and-where-to","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","date":"2021-04-18","arxiv_id":"2104.08786","n_code_links":2,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"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) · 7 unverified","official":null}},{"paper":"/paper/gpt3mix-leveraging-large-scale-language","slug":"gpt3mix-leveraging-large-scale-language","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","date":"2021-04-18","arxiv_id":"2104.08826","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver-ai/hypermix"],"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/natural-instructions-benchmarking","slug":"natural-instructions-benchmarking","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","date":"2021-04-18","arxiv_id":"2104.08773","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":1,"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":["allenai/natural-instructions","allenai/natural-instructions-v1"],"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","unlocated"]}}},{"paper":"/paper/the-power-of-scale-for-parameter-efficient","slug":"the-power-of-scale-for-parameter-efficient","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","date":"2021-04-18","arxiv_id":"2104.08691","n_code_links":12,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/prompt-tuning"],"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/an-adversarially-learned-turing-test-for","slug":"an-adversarially-learned-turing-test-for","title":"An Adversarially-Learned Turing Test for Dialog Generation Models","date":"2021-04-16","arxiv_id":"2104.08231","n_code_links":1,"syntology":null},{"paper":"/paper/surface-form-competition-why-the-highest","slug":"surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","date":"2021-04-16","arxiv_id":"2104.08315","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"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) · 0 unverified","official":{"repos":["peterwestuw/surface-form-competition"],"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/text2app-a-framework-for-creating-android","slug":"text2app-a-framework-for-creating-android","title":"Text2App: A Framework for Creating Android Apps from Text Descriptions","date":"2021-04-16","arxiv_id":"2104.08301","n_code_links":2,"syntology":null},{"paper":"/paper/meta-tuning-language-models-to-answer-prompts","slug":"meta-tuning-language-models-to-answer-prompts","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","date":"2021-04-10","arxiv_id":"2104.04670","n_code_links":1,"syntology":null},{"paper":"/paper/russian-paraphrasers-paraphrase-with","slug":"russian-paraphrasers-paraphrase-with","title":"Russian Paraphrasers: Paraphrase with Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"automatic-graph-partitioning-for-very-large","title":"Automatic Graph Partitioning for Very Large-scale Deep Learning","date":"2021-03-30","arxiv_id":"2103.16063","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-hate-speech-with-gpt-3","slug":"detecting-hate-speech-with-gpt-3","title":"Detecting Hate Speech with GPT-3","date":"2021-03-23","arxiv_id":"2103.12407","n_code_links":2,"syntology":null},{"paper":"/paper/calibrate-before-use-improving-few-shot","slug":"calibrate-before-use-improving-few-shot","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","date":"2021-02-19","arxiv_id":"2102.09690","n_code_links":5,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["tonyzhaozh/few-shot-learning"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/terapipe-token-level-pipeline-parallelism-for","slug":"terapipe-token-level-pipeline-parallelism-for","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","date":"2021-02-16","arxiv_id":"2102.07988","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":3,"n_instrument":4,"unverified":1,"pointer_only":8,"phrase":"7 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhuohan123/terapipe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"prompt-programming-for-large-language-models","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","date":"2021-02-15","arxiv_id":"2102.07350","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiversal-views-on-language-models","title":"Multiversal views on language models","date":"2021-02-12","arxiv_id":"2102.06391","n_code_links":0,"syntology":null},{"paper":"/paper/pipetransformer-automated-elastic-pipelining","slug":"pipetransformer-automated-elastic-pipelining","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","date":"2021-02-05","arxiv_id":"2102.03161","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":["Distributed-AI/PipeTransformer"],"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":"understanding-emails-and-drafting-responses","title":"Understanding Emails and Drafting Responses -- An Approach Using GPT-3","date":"2021-02-05","arxiv_id":"2102.03062","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-capabilities-limitations","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","date":"2021-02-04","arxiv_id":"2102.02503","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-depression-related-to-cannabis-a-knowledge","title":"\"Is depression related to cannabis?\": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision","date":"2021-02-01","arxiv_id":"2102.01222","n_code_links":0,"syntology":null},{"paper":"/paper/persistent-anti-muslim-bias-in-large-language","slug":"persistent-anti-muslim-bias-in-large-language","title":"Persistent Anti-Muslim Bias in Large Language Models","date":"2021-01-14","arxiv_id":"2101.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-multipurpose-are-language-models","title":"How Multipurpose Are Language Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/warp-word-level-adversarial-reprogramming","slug":"warp-word-level-adversarial-reprogramming","title":"WARP: Word-level Adversarial ReProgramming","date":"2021-01-01","arxiv_id":"2101.00121","n_code_links":1,"syntology":null},{"paper":"/paper/making-pre-trained-language-models-better-few","slug":"making-pre-trained-language-models-better-few","title":"Making Pre-trained Language Models Better Few-shot Learners","date":"2020-12-31","arxiv_id":"2012.15723","n_code_links":9,"syntology":{"ran":2,"of":9,"n_ran_checked":2,"n_instrument":0,"unverified":7,"pointer_only":7,"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) · 7 unverified","official":{"repos":["princeton-nlp/LM-BFF"],"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/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["EleutherAI/The-Pile"],"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":"revisiting-linformer-with-a-modified-self","title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-beyond-backpropagation-a-photonic-co","title":"Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment","date":"2020-12-11","arxiv_id":"2012.06373","n_code_links":0,"syntology":null},{"paper":"/paper/cpm-a-large-scale-generative-chinese-pre","slug":"cpm-a-large-scale-generative-chinese-pre","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","date":"2020-12-01","arxiv_id":"2012.00413","n_code_links":10,"syntology":null},{"paper":"/paper/increasing-learning-efficiency-of-self","slug":"increasing-learning-efficiency-of-self","title":"Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"do-fine-tuned-commonsense-language-models","title":"Do Fine-tuned Commonsense Language Models Really Generalize?","date":"2020-11-18","arxiv_id":"2011.09159","n_code_links":0,"syntology":null},{"paper":"/paper/comet-atomic-2020-on-symbolic-and-neural","slug":"comet-atomic-2020-on-symbolic-and-neural","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","date":"2020-10-12","arxiv_id":"2010.05953","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"7 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/comet-atomic-2020"],"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":["listed","official"]}}},{"paper":"/paper/toward-a-thermodynamics-of-meaning","slug":"toward-a-thermodynamics-of-meaning","title":"Toward a Thermodynamics of Meaning","date":"2020-09-24","arxiv_id":"2009.11963","n_code_links":1,"syntology":null},{"paper":"/paper/it-s-not-just-size-that-matters-small","slug":"it-s-not-just-size-that-matters-small","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","date":"2020-09-15","arxiv_id":"2009.07118","n_code_links":5,"syntology":null}],"record_sha256":"56aa08f81f0e58f4c1705c81a68440cdbf3ca5625b409510778267dab3f70a2b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}