{"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/30","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":30,"pages_in_order":38,"rows_per_page":100,"rows":[2901,3000],"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/29","next":"/method/linear-warmup-with-cosine-annealing/papers/31","papers":[{"paper":"/paper/rethinking-with-retrieval-faithful-large","slug":"rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","arxiv_id":"2301.00303","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeted-phishing-campaigns-using-large-scale","title":"Targeted Phishing Campaigns using Large Scale Language Models","date":"2022-12-30","arxiv_id":"2301.00665","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","n_code_links":5,"syntology":null},{"paper":null,"slug":"maximizing-use-case-specificity-through","title":"Maximizing Use-Case Specificity through Precision Model Tuning","date":"2022-12-29","arxiv_id":"2212.14206","n_code_links":0,"syntology":null},{"paper":"/paper/deepcuts-single-shot-interpretability-based","slug":"deepcuts-single-shot-interpretability-based","title":"DeepCuts: Single-Shot Interpretability based Pruning for BERT","date":"2022-12-27","arxiv_id":"2212.13392","n_code_links":1,"syntology":null},{"paper":null,"slug":"tegformer-topic-to-essay-generation-with-good","title":"TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence","date":"2022-12-27","arxiv_id":"2212.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-generate","title":"Using Large Language Models to Generate Engaging Captions for Data Visualizations","date":"2022-12-27","arxiv_id":"2212.14047","n_code_links":0,"syntology":null},{"paper":null,"slug":"biologically-inspired-design-concept","title":"Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers","date":"2022-12-26","arxiv_id":"2212.13196","n_code_links":0,"syntology":null},{"paper":"/paper/benchmark-for-uncertainty-robustness-in-self","slug":"benchmark-for-uncertainty-robustness-in-self","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","date":"2022-12-23","arxiv_id":"2212.12411","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-larger-transformer","title":"Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?","date":"2022-12-23","arxiv_id":"2212.12131","n_code_links":0,"syntology":null},{"paper":"/paper/entropy-and-distance-based-predictors-from","slug":"entropy-and-distance-based-predictors-from","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","date":"2022-12-21","arxiv_id":"2212.11185","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["byungdoh/attn_dist"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"jasmine-arabic-gpt-models-for-few-shot","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","date":"2022-12-21","arxiv_id":"2212.10755","n_code_links":0,"syntology":null},{"paper":null,"slug":"kl-regularized-normalization-framework-for","title":"KL Regularized Normalization Framework for Low Resource Tasks","date":"2022-12-21","arxiv_id":"2212.11275","n_code_links":0,"syntology":null},{"paper":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","n_code_links":1,"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":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"controllable-text-generation-with-language","title":"Controllable Text Generation with Language Constraints","date":"2022-12-20","arxiv_id":"2212.10466","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-have-coherent-mental","slug":"do-language-models-have-coherent-mental","title":"Do language models have coherent mental models of everyday things?","date":"2022-12-20","arxiv_id":"2212.10029","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["allenai/everyday-things"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/docasref-a-pilot-empirical-study-on","slug":"docasref-a-pilot-empirical-study-on","title":"DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely","date":"2022-12-20","arxiv_id":"2212.10013","n_code_links":1,"syntology":null},{"paper":null,"slug":"generic-temporal-reasoning-with-differential","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","date":"2022-12-20","arxiv_id":"2212.10467","n_code_links":0,"syntology":null},{"paper":null,"slug":"go-tuning-improving-zero-shot-learning","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","date":"2022-12-20","arxiv_id":"2212.10461","n_code_links":0,"syntology":null},{"paper":"/paper/is-gpt-3-a-good-data-annotator","slug":"is-gpt-3-a-good-data-annotator","title":"Is GPT-3 a Good Data Annotator?","date":"2022-12-20","arxiv_id":"2212.10450","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-3-a-psychopath-evaluating-large","title":"Evaluating Psychological Safety of Large Language Models","date":"2022-12-20","arxiv_id":"2212.10529","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-reasoning-teachers","slug":"large-language-models-are-reasoning-teachers","title":"Large Language Models Are Reasoning Teachers","date":"2022-12-20","arxiv_id":"2212.10071","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itsnamgyu/reasoning-teacher"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pairreranker-pairwise-reranking-for-natural","title":"PairReranker: Pairwise Reranking for Natural Language Generation","date":"2022-12-20","arxiv_id":"2212.10555","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-your-tone-introducing-a-new","slug":"pay-attention-to-your-tone-introducing-a-new","title":"Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite","date":"2022-12-20","arxiv_id":"2212.10190","n_code_links":1,"syntology":null},{"paper":null,"slug":"true-detective-a-challenging-benchmark-for","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","date":"2022-12-20","arxiv_id":"2212.10114","n_code_links":0,"syntology":null},{"paper":"/paper/why-can-gpt-learn-in-context-language-models","slug":"why-can-gpt-learn-in-context-language-models","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","date":"2022-12-20","arxiv_id":"2212.10559","n_code_links":1,"syntology":null},{"paper":"/paper/emergent-analogical-reasoning-in-large","slug":"emergent-analogical-reasoning-in-large","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","arxiv_id":"2212.09196","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["taylorwwebb/emergent_analogies_llm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-human-language-model-interaction","slug":"evaluating-human-language-model-interaction","title":"Evaluating Human-Language Model Interaction","date":"2022-12-19","arxiv_id":"2212.09746","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-reasoners-with-self","slug":"large-language-models-are-reasoners-with-self","title":"Large Language Models are Better Reasoners with Self-Verification","date":"2022-12-19","arxiv_id":"2212.09561","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["WENGSYX/Self-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/lens-a-learnable-evaluation-metric-for-text","slug":"lens-a-learnable-evaluation-metric-for-text","title":"LENS: A Learnable Evaluation Metric for Text Simplification","date":"2022-12-19","arxiv_id":"2212.09739","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","n_code_links":2,"syntology":null},{"paper":"/paper/the-case-for-4-bit-precision-k-bit-inference","slug":"the-case-for-4-bit-precision-k-bit-inference","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","date":"2022-12-19","arxiv_id":"2212.09720","n_code_links":1,"syntology":null},{"paper":"/paper/can-retriever-augmented-language-models","slug":"can-retriever-augmented-language-models","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","date":"2022-12-18","arxiv_id":"2212.09146","n_code_links":1,"syntology":null},{"paper":null,"slug":"murmur-modular-multi-step-reasoning-for-semi","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","date":"2022-12-16","arxiv_id":"2212.08607","n_code_links":0,"syntology":null},{"paper":"/paper/self-prompting-large-language-models-for-open","slug":"self-prompting-large-language-models-for-open","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","date":"2022-12-16","arxiv_id":"2212.08635","n_code_links":1,"syntology":null},{"paper":"/paper/revisiting-the-gold-standard-grounding","slug":"revisiting-the-gold-standard-grounding","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","date":"2022-12-15","arxiv_id":"2212.07981","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yale-lily/rose"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/crepe-can-vision-language-foundation-models","slug":"crepe-can-vision-language-foundation-models","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","date":"2022-12-13","arxiv_id":"2212.07796","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["raivnlab/crepe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"/paper/elixir-train-a-large-language-model-on-a","slug":"elixir-train-a-large-language-model-on-a","title":"Elixir: Train a Large Language Model on a Small GPU Cluster","date":"2022-12-10","arxiv_id":"2212.05339","n_code_links":2,"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":null,"slug":"the-turing-deception","title":"The Turing Deception","date":"2022-12-09","arxiv_id":"2212.06721","n_code_links":0,"syntology":null},{"paper":null,"slug":"trbllmaker-transformer-reads-between-lyrics","title":"TRBLLmaker -- Transformer Reads Between Lyrics Lines maker","date":"2022-12-09","arxiv_id":"2212.04917","n_code_links":0,"syntology":null},{"paper":"/paper/explain-to-me-like-i-am-five-sentence","slug":"explain-to-me-like-i-am-five-sentence","title":"Explain to me like I am five -- Sentence Simplification Using Transformers","date":"2022-12-08","arxiv_id":"2212.04595","n_code_links":1,"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":"modern-french-poetry-generation-with-roberta","title":"Modern French Poetry Generation with RoBERTa and GPT-2","date":"2022-12-06","arxiv_id":"2212.02911","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-driven-co-speech-gesture-video","title":"Audio-Driven Co-Speech Gesture Video Generation","date":"2022-12-05","arxiv_id":"2212.02350","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-factual-news","title":"Automatic Generation of Factual News Headlines in Finnish","date":"2022-12-05","arxiv_id":"2212.02170","n_code_links":0,"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":null,"slug":"quadapter-adapter-for-gpt-2-quantization","title":"Quadapter: Adapter for GPT-2 Quantization","date":"2022-11-30","arxiv_id":"2211.16912","n_code_links":0,"syntology":null},{"paper":null,"slug":"outfit-generation-and-recommendation-an","title":"Outfit Generation and Recommendation -- An Experimental Study","date":"2022-11-29","arxiv_id":"2211.16353","n_code_links":0,"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":"/paper/scientific-and-creative-analogies-in","slug":"scientific-and-creative-analogies-in","title":"Scientific and Creative Analogies in Pretrained Language Models","date":"2022-11-28","arxiv_id":"2211.15268","n_code_links":2,"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/exploring-the-efficacy-of-pre-trained","slug":"exploring-the-efficacy-of-pre-trained","title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","date":"2022-11-21","arxiv_id":"2211.11216","n_code_links":2,"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/pointclip-v2-adapting-clip-for-powerful-3d","slug":"pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yangyangyang127/pointclip_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"conceptor-aided-debiasing-of-contextualized","title":"Conceptor-Aided Debiasing of Large Language Models","date":"2022-11-20","arxiv_id":"2211.11087","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","n_code_links":0,"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/random-ltd-random-and-layerwise-token","slug":"random-ltd-random-and-layerwise-token","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","date":"2022-11-17","arxiv_id":"2211.11586","n_code_links":1,"syntology":null},{"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":null,"slug":"tsmind-alibaba-and-soochow-university-s","title":"TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task","date":"2022-11-16","arxiv_id":"2211.08987","n_code_links":0,"syntology":null},{"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":"textual-data-augmentation-for-patient","title":"Textual Data Augmentation for Patient Outcomes Prediction","date":"2022-11-13","arxiv_id":"2211.06778","n_code_links":0,"syntology":null},{"paper":"/paper/what-would-harry-say-building-dialogue-agents","slug":"what-would-harry-say-building-dialogue-agents","title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","date":"2022-11-13","arxiv_id":"2211.06869","n_code_links":1,"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/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","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":["jmichaelov/collateral-facilitation"],"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/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":"/paper/interpretability-in-the-wild-a-circuit-for","slug":"interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","arxiv_id":"2211.00593","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["redwoodresearch/easy-transformer"],"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/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"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":["davidhuji/capdec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/gptq-accurate-post-training-quantization-for","slug":"gptq-accurate-post-training-quantization-for","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","date":"2022-10-31","arxiv_id":"2210.17323","n_code_links":17,"syntology":{"ran":5,"of":15,"n_ran_checked":2,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["ist-daslab/gptq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/ssd-lm-semi-autoregressive-simplex-based","slug":"ssd-lm-semi-autoregressive-simplex-based","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","date":"2022-10-31","arxiv_id":"2210.17432","n_code_links":2,"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/probing-for-targeted-syntactic-knowledge","slug":"probing-for-targeted-syntactic-knowledge","title":"Probing for targeted syntactic knowledge through grammatical error detection","date":"2022-10-28","arxiv_id":"2210.16228","n_code_links":1,"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":"trscore-a-novel-gpt-based-readability-scorer","title":"TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection","date":"2022-10-27","arxiv_id":"2210.15104","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-robustness-of-prefix-tuning-in","title":"Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis","date":"2022-10-26","arxiv_id":"2211.05584","n_code_links":0,"syntology":null},{"paper":null,"slug":"ielm-an-open-information-extraction-benchmark","title":"IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models","date":"2022-10-25","arxiv_id":"2210.14128","n_code_links":0,"syntology":null},{"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/emergent-world-representations-exploring-a","slug":"emergent-world-representations-exploring-a","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","date":"2022-10-24","arxiv_id":"2210.13382","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["likenneth/othello_world"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"cd4b83475fdb0bca1b57f5f2355a1d64b8b3ecab2c4bd44b0709603e1c3362ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}