{"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/cosine-annealing/papers/30","list_of":"/method/cosine-annealing","method":"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":40,"rows_per_page":100,"rows":[2901,3000],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/29","next":"/method/cosine-annealing/papers/31","papers":[{"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":"/paper/perfect-is-the-enemy-of-test-oracle","slug":"perfect-is-the-enemy-of-test-oracle","title":"Perfect is the enemy of test oracle","date":"2023-02-03","arxiv_id":"2302.01488","n_code_links":1,"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":null,"slug":"a-2-uav-application-aware-content-and-network","title":"A$^2$-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems","date":"2023-01-16","arxiv_id":"2301.06363","n_code_links":0,"syntology":null},{"paper":"/paper/tedb-system-description-to-a-shared-task-on","slug":"tedb-system-description-to-a-shared-task-on","title":"TEDB System Description to a Shared Task on Euphemism Detection 2022","date":"2023-01-16","arxiv_id":"2301.06602","n_code_links":1,"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},{"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":null,"slug":"traffic-sign-detection-and-recognition-using","title":"Traffic sign detection and recognition using event camera image reconstruction","date":"2022-12-16","arxiv_id":"2212.08387","n_code_links":0,"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/comparison-of-deep-object-detectors-on-a-new","slug":"comparison-of-deep-object-detectors-on-a-new","title":"Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset","date":"2022-12-12","arxiv_id":"2212.06218","n_code_links":2,"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":"image-based-fire-detection-in-industrial","title":"Image-Based Fire Detection in Industrial Environments with YOLOv4","date":"2022-12-09","arxiv_id":"2212.04786","n_code_links":0,"syntology":null},{"paper":null,"slug":"pacman-a-framework-for-pulse-oximeter-digit","title":"PACMAN: a framework for pulse oximeter digit detection and reading in a low-resource setting","date":"2022-12-09","arxiv_id":"2212.04964","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":null,"slug":"visual-detection-of-personal-protective","title":"Visual Detection of Personal Protective Equipment and Safety Gear on Industry Workers","date":"2022-12-09","arxiv_id":"2212.04794","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}],"record_sha256":"1a067360b8322bd71a404494aaa5f09edd7ef4a1c6b61e890e293976808a1159","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}