{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-warmup-with-cosine-annealing/papers/29","list_of":"/method/linear-warmup-with-cosine-annealing","method":"Linear Warmup With Cosine Annealing","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":29,"pages_in_order":38,"rows_per_page":100,"rows":[2801,2900],"of":3797,"counts":{"archive_papers_tagged":3797,"with_a_code_link":1655,"where_syntology_ran_a_sample":602,"not_listed_spam_title":0,"listed":3797,"listed_where_code_ran":602,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":490,"every_run_a_failure_of_syntologys_instrument":112,"listed_with_a_run_with_no_instrument_failure":490,"listed_every_run_a_failure_of_syntologys_instrument":112,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-warmup-with-cosine-annealing","prev":"/method/linear-warmup-with-cosine-annealing/papers/28","next":"/method/linear-warmup-with-cosine-annealing/papers/30","papers":[{"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/towards-zero-shot-functional-compositionality","slug":"towards-zero-shot-functional-compositionality","title":"Towards Zero-Shot Functional Compositionality of Language Models","date":"2023-03-06","arxiv_id":"2303.03103","n_code_links":1,"syntology":null},{"paper":null,"slug":"fqp-2-0-industry-trend-analysis-via","title":"Industry Risk Assessment via Hierarchical Financial Data Using Stock Market Sentiment Indicators","date":"2023-03-05","arxiv_id":"2303.02707","n_code_links":0,"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/information-restricted-neural-language-models","slug":"information-restricted-neural-language-models","title":"Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context","date":"2023-02-28","arxiv_id":"2302.14389","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":["alexandrepsq/information-restrited-nlms"],"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":"/paper/large-language-models-are-state-of-the-art","slug":"large-language-models-are-state-of-the-art","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","date":"2023-02-28","arxiv_id":"2302.14520","n_code_links":4,"syntology":null},{"paper":null,"slug":"sampled-transformer-for-point-sets","title":"Sampled Transformer for Point Sets","date":"2023-02-28","arxiv_id":"2302.14346","n_code_links":0,"syntology":null},{"paper":"/paper/inseq-an-interpretability-toolkit-for","slug":"inseq-an-interpretability-toolkit-for","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","date":"2023-02-27","arxiv_id":"2302.13942","n_code_links":2,"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/large-scale-multi-modal-pre-trained-models-a","slug":"large-scale-multi-modal-pre-trained-models-a","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","date":"2023-02-20","arxiv_id":"2302.10035","n_code_links":1,"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/how-good-are-gpt-models-at-machine","slug":"how-good-are-gpt-models-at-machine","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","date":"2023-02-18","arxiv_id":"2302.09210","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/gpt-mt"],"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"]}}},{"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":"/paper/conveying-the-predicted-future-to-users-a","slug":"conveying-the-predicted-future-to-users-a","title":"Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction","date":"2023-02-17","arxiv_id":"2302.09122","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":"/paper/pac-prediction-sets-for-large-language-models","slug":"pac-prediction-sets-for-large-language-models","title":"PAC Prediction Sets for Large Language Models of Code","date":"2023-02-17","arxiv_id":"2302.08703","n_code_links":1,"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":null,"slug":"foundation-models-for-natural-language","title":"Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media","date":"2023-02-16","arxiv_id":"2302.08575","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":null,"slug":"commonsense-reasoning-for-conversational-ai-a","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","date":"2023-02-15","arxiv_id":"2302.07926","n_code_links":0,"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/tree-based-representation-and-generation-of","slug":"tree-based-representation-and-generation-of","title":"Tree-Based Representation and Generation of Natural and Mathematical Language","date":"2023-02-15","arxiv_id":"2302.07974","n_code_links":1,"syntology":null},{"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":null,"slug":"artificial-intelligence-in-psychology","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","date":"2023-02-13","arxiv_id":"2302.07267","n_code_links":0,"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":"academic-writing-with-gpt-3-5-reflections-on","title":"Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency","date":"2023-02-12","arxiv_id":"2304.11079","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":"/paper/combat-ai-with-ai-counteract-machine","slug":"combat-ai-with-ai-counteract-machine","title":"Combat AI With AI: Counteract Machine-Generated Fake Restaurant Reviews on Social Media","date":"2023-02-10","arxiv_id":"2302.07731","n_code_links":1,"syntology":null},{"paper":"/paper/fairpy-a-toolkit-for-evaluation-of-social","slug":"fairpy-a-toolkit-for-evaluation-of-social","title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models","date":"2023-02-10","arxiv_id":"2302.05508","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtr-ctrl-instrument-and-genre-conditioning","title":"GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformers","date":"2023-02-10","arxiv_id":"2302.05393","n_code_links":0,"syntology":null},{"paper":"/paper/the-wisdom-of-hindsight-makes-language-models","slug":"the-wisdom-of-hindsight-makes-language-models","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","date":"2023-02-10","arxiv_id":"2302.05206","n_code_links":1,"syntology":null},{"paper":"/paper/translating-natural-language-to-planning","slug":"translating-natural-language-to-planning","title":"Translating Natural Language to Planning Goals with Large-Language Models","date":"2023-02-10","arxiv_id":"2302.05128","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-by-you-better-than-me-chatgpt3-as","title":"Better by you, better than me, chatgpt3 as writing assistance in students essays","date":"2023-02-09","arxiv_id":"2302.04536","n_code_links":0,"syntology":null},{"paper":"/paper/generating-a-structured-summary-of-numerous","slug":"generating-a-structured-summary-of-numerous","title":"Generating a Structured Summary of Numerous Academic Papers: Dataset and Method","date":"2023-02-09","arxiv_id":"2302.04580","n_code_links":1,"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":"nationality-bias-in-text-generation","title":"Nationality Bias in Text Generation","date":"2023-02-05","arxiv_id":"2302.02463","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantized-distributed-training-of-large","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","date":"2023-02-05","arxiv_id":"2302.02390","n_code_links":0,"syntology":null},{"paper":"/paper/realtabformer-generating-realistic-relational","slug":"realtabformer-generating-realistic-relational","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","date":"2023-02-04","arxiv_id":"2302.02041","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["avsolatorio/realtabformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"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":"/paper/semantic-coherence-markers-for-the-early","slug":"semantic-coherence-markers-for-the-early","title":"Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease","date":"2023-02-02","arxiv_id":"2302.01025","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-language-reveals-about-perception","title":"Large language models predict human sensory judgments across six modalities","date":"2023-02-02","arxiv_id":"2302.01308","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-leakage-of-personally-identifiable","slug":"analyzing-leakage-of-personally-identifiable","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","date":"2023-02-01","arxiv_id":"2302.00539","n_code_links":1,"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":"an-comparative-analysis-of-different-pitch","title":"An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generation","date":"2023-01-31","arxiv_id":"2301.13383","n_code_links":0,"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":null,"slug":"incorporating-knowledge-into-document","title":"The Exploration of Knowledge-Preserving Prompts for Document Summarisation","date":"2023-01-27","arxiv_id":"2301.11719","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-latent-variable-1","slug":"large-language-models-are-latent-variable-1","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","date":"2023-01-27","arxiv_id":"2301.11916","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["wangxinyilinda/concept-based-demonstration-selection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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":"a-stability-analysis-of-fine-tuning-a-pre","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","date":"2023-01-24","arxiv_id":"2301.09820","n_code_links":0,"syntology":null},{"paper":"/paper/audience-centric-natural-language-generation","slug":"audience-centric-natural-language-generation","title":"Audience-Centric Natural Language Generation via Style Infusion","date":"2023-01-24","arxiv_id":"2301.10283","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/t2m-gpt-generating-human-motion-from-textual","slug":"t2m-gpt-generating-human-motion-from-textual","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","date":"2023-01-15","arxiv_id":"2301.06052","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Mael-zys/T2M-GPT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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":null,"slug":"automatic-generation-of-german-drama-texts","title":"Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models","date":"2023-01-08","arxiv_id":"2301.03119","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":null,"slug":"sequentially-controlled-text-generation-1","title":"Sequentially Controlled Text Generation","date":"2023-01-05","arxiv_id":"2301.02299","n_code_links":0,"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":"generating-human-motion-from-textual","title":"Generating Human Motion From Textual Descriptions With Discrete Representations","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"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}],"record_sha256":"bd28b467ed6e331908d8aa0ebc9f8eeeaa87a8832483cdd65da88d0f1470d6ea","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}