{"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/22","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":22,"pages_in_order":38,"rows_per_page":100,"rows":[2101,2200],"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/21","next":"/method/linear-warmup-with-cosine-annealing/papers/23","papers":[{"paper":"/paper/memory-gym-partially-observable-challenges-to","slug":"memory-gym-partially-observable-challenges-to","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","date":"2023-09-29","arxiv_id":"2309.17207","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":["marcometer/endless-memory-gym"],"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":"revolutionizing-mobile-interaction-enabling-a","title":"Revolutionizing Mobile Interaction: Enabling a 3 Billion Parameter GPT LLM on Mobile","date":"2023-09-29","arxiv_id":"2310.01434","n_code_links":0,"syntology":null},{"paper":null,"slug":"split-and-merge-aligning-position-biases-in","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","date":"2023-09-29","arxiv_id":"2310.01432","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-and-inference-of-large-language","title":"Training and inference of large language models using 8-bit floating point","date":"2023-09-29","arxiv_id":"2309.17224","n_code_links":0,"syntology":null},{"paper":null,"slug":"ae-gpt-using-large-language-models-to-extract","title":"AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events","date":"2023-09-28","arxiv_id":"2309.16150","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-fathom-benchmarking-large-language-models","slug":"gpt-fathom-benchmarking-large-language-models","title":"GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond","date":"2023-09-28","arxiv_id":"2309.16583","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["gpt-fathom/gpt-fathom"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-model-soft-ideologization-via","title":"Large Language Model Soft Ideologization via AI-Self-Consciousness","date":"2023-09-28","arxiv_id":"2309.16167","n_code_links":0,"syntology":null},{"paper":null,"slug":"stress-testing-chain-of-thought-prompting-for","title":"Stress Testing Chain-of-Thought Prompting for Large Language Models","date":"2023-09-28","arxiv_id":"2309.16621","n_code_links":0,"syntology":null},{"paper":"/paper/mindgpt-interpreting-what-you-see-with-non","slug":"mindgpt-interpreting-what-you-see-with-non","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","date":"2023-09-27","arxiv_id":"2309.15729","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"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) · 4 unverified","official":{"repos":["jxuanc/mindgpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nlpbench-evaluating-large-language-models-on","slug":"nlpbench-evaluating-large-language-models-on","title":"NLPBench: Evaluating Large Language Models on Solving NLP Problems","date":"2023-09-27","arxiv_id":"2309.15630","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-artificial","title":"Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models","date":"2023-09-26","arxiv_id":"2309.14735","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-small-language-models-with-prompt","title":"Exploring Small Language Models with Prompt-Learning Paradigm for Efficient Domain-Specific Text Classification","date":"2023-09-26","arxiv_id":"2309.14779","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-catch-an-ai-liar-lie-detection-in","slug":"how-to-catch-an-ai-liar-lie-detection-in","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","date":"2023-09-26","arxiv_id":"2309.15840","n_code_links":1,"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":["lorypack/llm-liedetector"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rankvicuna-zero-shot-listwise-document","slug":"rankvicuna-zero-shot-listwise-document","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","date":"2023-09-26","arxiv_id":"2309.15088","n_code_links":3,"syntology":null},{"paper":"/paper/supersonic-learning-to-generate-source-code","slug":"supersonic-learning-to-generate-source-code","title":"Supersonic: Learning to Generate Source Code Optimizations in C/C++","date":"2023-09-26","arxiv_id":"2309.14846","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-cognitive-maps-and-planning-in","title":"Evaluating Cognitive Maps and Planning in Large Language Models with CogEval","date":"2023-09-25","arxiv_id":"2309.15129","n_code_links":0,"syntology":null},{"paper":"/paper/loggpt-log-anomaly-detection-via-gpt","slug":"loggpt-log-anomaly-detection-via-gpt","title":"LogGPT: Log Anomaly Detection via GPT","date":"2023-09-25","arxiv_id":"2309.14482","n_code_links":1,"syntology":null},{"paper":null,"slug":"watch-your-language-large-language-models-and","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","date":"2023-09-25","arxiv_id":"2309.14517","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-the-most-sinfully-decadent-cake-ever","title":"Does the \"most sinfully decadent cake ever\" taste good? Answering Yes/No Questions from Figurative Contexts","date":"2023-09-24","arxiv_id":"2309.13748","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-is-not-always-believing-invisible","slug":"seeing-is-not-always-believing-invisible","title":"Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models","date":"2023-09-24","arxiv_id":"2309.13579","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-chat-about-boring-problems-studying-gpt","title":"A Chat About Boring Problems: Studying GPT-based text normalization","date":"2023-09-23","arxiv_id":"2309.13426","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-cognitive","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","date":"2023-09-23","arxiv_id":"2309.13356","n_code_links":0,"syntology":null},{"paper":"/paper/amplify-attention-based-mixup-for-performance","slug":"amplify-attention-based-mixup-for-performance","title":"AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer","date":"2023-09-22","arxiv_id":"2309.12689","n_code_links":1,"syntology":null},{"paper":null,"slug":"benllmeval-a-comprehensive-evaluation-into","title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","date":"2023-09-22","arxiv_id":"2309.13173","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-emotion-estimation-from-image","title":"Contextual Emotion Estimation from Image Captions","date":"2023-09-22","arxiv_id":"2309.13136","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-and-control-mechanisms","slug":"large-language-models-and-control-mechanisms","title":"Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts","date":"2023-09-22","arxiv_id":"2309.13202","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-are-also-good","title":"Large Language Models Are Also Good Prototypical Commonsense Reasoners","date":"2023-09-22","arxiv_id":"2309.13165","n_code_links":0,"syntology":null},{"paper":null,"slug":"spion-layer-wise-sparse-training-of","title":"SPION: Layer-Wise Sparse Training of Transformer via Convolutional Flood Filling","date":"2023-09-22","arxiv_id":"2309.12578","n_code_links":0,"syntology":null},{"paper":"/paper/a-chinese-prompt-attack-dataset-for-llms-with","slug":"a-chinese-prompt-attack-dataset-for-llms-with","title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","date":"2023-09-21","arxiv_id":"2309.11830","n_code_links":2,"syntology":null},{"paper":"/paper/bad-actor-good-advisor-exploring-the-role-of","slug":"bad-actor-good-advisor-exploring-the-role-of","title":"Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection","date":"2023-09-21","arxiv_id":"2309.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"constraints-first-a-new-mdd-based-model-to","title":"Constraints First: A New MDD-based Model to Generate Sentences Under Constraints","date":"2023-09-21","arxiv_id":"2309.12415","n_code_links":0,"syntology":null},{"paper":"/paper/metamath-bootstrap-your-own-mathematical","slug":"metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","arxiv_id":"2309.12284","n_code_links":1,"syntology":{"ran":15,"of":22,"n_ran_checked":1,"n_instrument":14,"unverified":7,"pointer_only":0,"phrase":"15 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; 14 where Syntology's instrument failed) · 7 unverified","official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/random-access-infinite-context-length-for","slug":"random-access-infinite-context-length-for","title":"Random-Access Infinite Context Length for Transformers","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tart-a-plug-and-play-transformer-module-for","slug":"tart-a-plug-and-play-transformer-module-for","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-cambridge-law-corpus-a-corpus-for-legal-1","slug":"the-cambridge-law-corpus-a-corpus-for-legal-1","title":"The Cambridge Law Corpus: A Dataset for Legal AI Research","date":"2023-09-21","arxiv_id":"2309.12269","n_code_links":0,"syntology":null},{"paper":"/paper/the-reversal-curse-llms-trained-on-a-is-b","slug":"the-reversal-curse-llms-trained-on-a-is-b","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","date":"2023-09-21","arxiv_id":"2309.12288","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"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) · 2 unverified","official":{"repos":["lukasberglund/reversal_curse"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"toa-task-oriented-active-vqa","title":"TOA: Task-oriented Active VQA","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-paradigm-shift-in-machine-translation","slug":"a-paradigm-shift-in-machine-translation","title":"A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models","date":"2023-09-20","arxiv_id":"2309.11674","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":["fe1ixxu/alma"],"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":"/paper/controlled-generation-with-prompt-insertion","slug":"controlled-generation-with-prompt-insertion","title":"Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction","date":"2023-09-20","arxiv_id":"2309.11439","n_code_links":1,"syntology":null},{"paper":"/paper/design-of-chain-of-thought-in-math-problem","slug":"design-of-chain-of-thought-in-math-problem","title":"Design of Chain-of-Thought in Math Problem Solving","date":"2023-09-20","arxiv_id":"2309.11054","n_code_links":1,"syntology":null},{"paper":null,"slug":"fictional-worlds-real-connections-developing","title":"Fictional Worlds, Real Connections: Developing Community Storytelling Social Chatbots through LLMs","date":"2023-09-20","arxiv_id":"2309.11478","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-in-mafia-like-game-simulation","title":"Generative AI in Mafia-like Game Simulation","date":"2023-09-20","arxiv_id":"2309.11672","n_code_links":0,"syntology":null},{"paper":"/paper/safurai-001-new-qualitative-approach-for-code","slug":"safurai-001-new-qualitative-approach-for-code","title":"Safurai 001: New Qualitative Approach for Code LLM Evaluation","date":"2023-09-20","arxiv_id":"2309.11385","n_code_links":1,"syntology":null},{"paper":"/paper/sequence-to-sequence-spanish-pre-trained","slug":"sequence-to-sequence-spanish-pre-trained","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","date":"2023-09-20","arxiv_id":"2309.11259","n_code_links":1,"syntology":null},{"paper":"/paper/the-languini-kitchen-enabling-language","slug":"the-languini-kitchen-enabling-language","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","date":"2023-09-20","arxiv_id":"2309.11197","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-as-the-medium-multimodal-video","title":"Language as the Medium: Multimodal Video Classification through text only","date":"2023-09-19","arxiv_id":"2309.10783","n_code_links":0,"syntology":null},{"paper":null,"slug":"rigorously-assessing-natural-language","title":"Rigorously Assessing Natural Language Explanations of Neurons","date":"2023-09-19","arxiv_id":"2309.10312","n_code_links":0,"syntology":null},{"paper":null,"slug":"writer-defined-ai-personas-for-on-demand","title":"Writer-Defined AI Personas for On-Demand Feedback Generation","date":"2023-09-19","arxiv_id":"2309.10433","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-for-anti-cancer-drug","title":"Evaluation of GPT-3 for Anti-Cancer Drug Sensitivity Prediction","date":"2023-09-18","arxiv_id":"2309.10016","n_code_links":0,"syntology":null},{"paper":"/paper/recap-retrieval-augmented-audio-captioning","slug":"recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"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) · 3 unverified","official":{"repos":["sreyan88/recap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-ontology-construction-with-language","title":"Towards Ontology Construction with Language Models","date":"2023-09-18","arxiv_id":"2309.09898","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-decoding-improves-reasoning-in","title":"Contrastive Decoding Improves Reasoning in Large Language Models","date":"2023-09-17","arxiv_id":"2309.09117","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-gpt-models-discover-moral-dimensions","title":"Do Large GPT Models Discover Moral Dimensions in Language Representations? A Topological Study Of Sentence Embeddings","date":"2023-09-17","arxiv_id":"2309.09397","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-cooking-recipes-to-robot-task-trees","title":"From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network","date":"2023-09-17","arxiv_id":"2309.09181","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoder-only-architecture-for-speech","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation","date":"2023-09-16","arxiv_id":"2309.08876","n_code_links":0,"syntology":null},{"paper":"/paper/struc-bench-are-large-language-models-really","slug":"struc-bench-are-large-language-models-really","title":"Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?","date":"2023-09-16","arxiv_id":"2309.08963","n_code_links":1,"syntology":null},{"paper":"/paper/a-modern-turkish-poet-fine-tuned-gpt-2","slug":"a-modern-turkish-poet-fine-tuned-gpt-2","title":"A Modern Turkish Poet: Fine-Tuned GPT-2","date":"2023-09-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/advancing-the-evaluation-of-traditional","slug":"advancing-the-evaluation-of-traditional","title":"Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite","date":"2023-09-15","arxiv_id":"2309.08448","n_code_links":1,"syntology":null},{"paper":"/paper/casteist-but-not-racist-quantifying","slug":"casteist-but-not-racist-quantifying","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","date":"2023-09-15","arxiv_id":"2309.08573","n_code_links":1,"syntology":null},{"paper":"/paper/connecting-large-language-models-with","slug":"connecting-large-language-models-with","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","date":"2023-09-15","arxiv_id":"2309.08532","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":3,"n_instrument":8,"unverified":2,"pointer_only":0,"phrase":"11 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; 8 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/cure-the-headache-of-transformers-via","slug":"cure-the-headache-of-transformers-via","title":"CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending","date":"2023-09-15","arxiv_id":"2309.08646","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-lab-next-generation-of-optimal-chemistry","title":"GPT-Lab: Next Generation Of Optimal Chemistry Discovery By GPT Driven Robotic Lab","date":"2023-09-15","arxiv_id":"2309.16721","n_code_links":0,"syntology":null},{"paper":"/paper/iclef-in-context-learning-with-expert","slug":"iclef-in-context-learning-with-expert","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","date":"2023-09-15","arxiv_id":"2309.08583","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-for-failure-mode","slug":"large-language-models-for-failure-mode","title":"Large Language Models for Failure Mode Classification: An Investigation","date":"2023-09-15","arxiv_id":"2309.08181","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-evaluation-of-prompting","title":"An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing","date":"2023-09-14","arxiv_id":"2309.08008","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-nature-of-large-language-models","title":"Assessing the nature of large language models: A caution against anthropocentrism","date":"2023-09-14","arxiv_id":"2309.07683","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-mt-competitive-for-high-but-not-low","slug":"chatgpt-mt-competitive-for-high-but-not-low","title":"ChatGPT MT: Competitive for High- (but not Low-) Resource Languages","date":"2023-09-14","arxiv_id":"2309.07423","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["cmu-llab/gpt_mt_benchmark"],"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":"two-timin-repairing-smart-contracts-with-a","title":"Two Timin': Repairing Smart Contracts With A Two-Layered Approach","date":"2023-09-14","arxiv_id":"2309.07841","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-can-infer-psychological","title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","date":"2023-09-13","arxiv_id":"2309.08631","n_code_links":0,"syntology":null},{"paper":"/paper/traveling-words-a-geometric-interpretation-of","slug":"traveling-words-a-geometric-interpretation-of","title":"Traveling Words: A Geometric Interpretation of Transformers","date":"2023-09-13","arxiv_id":"2309.07315","n_code_links":1,"syntology":null},{"paper":"/paper/2309-05973","slug":"2309-05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","date":"2023-09-12","arxiv_id":"2309.05973","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"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) · 3 unverified","official":{"repos":["xanderdavies/circuit-breaking"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2309-06112","title":"Characterizing Latent Perspectives of Media Houses Towards Public Figures","date":"2023-09-12","arxiv_id":"2309.06112","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-llama-2-and-gpt-3-llms-for-hpc","title":"Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation","date":"2023-09-12","arxiv_id":"2309.07103","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-ontology","slug":"exploring-large-language-models-for-ontology","title":"Exploring Large Language Models for Ontology Alignment","date":"2023-09-12","arxiv_id":"2309.07172","n_code_links":1,"syntology":null},{"paper":null,"slug":"strategic-behavior-of-large-language-models","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","date":"2023-09-12","arxiv_id":"2309.05898","n_code_links":0,"syntology":null},{"paper":"/paper/the-moral-machine-experiment-on-large","slug":"the-moral-machine-experiment-on-large","title":"The Moral Machine Experiment on Large Language Models","date":"2023-09-12","arxiv_id":"2309.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-the-potential-of-large-language","title":"Unveiling the potential of large language models in generating semantic and cross-language clones","date":"2023-09-12","arxiv_id":"2309.06424","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-analysis-gpts-across-time-in-legal","title":"Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task","date":"2023-09-11","arxiv_id":"2309.05501","n_code_links":0,"syntology":null},{"paper":"/paper/memory-injections-correcting-multi-hop","slug":"memory-injections-correcting-multi-hop","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","date":"2023-09-11","arxiv_id":"2309.05605","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["msakarvadia/memory_injections"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparseswin-swin-transformer-with-sparse","slug":"sparseswin-swin-transformer-with-sparse","title":"SparseSwin: Swin Transformer with Sparse Transformer Block","date":"2023-09-11","arxiv_id":"2309.05224","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-learning-with-minimum-instruction","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","date":"2023-09-11","arxiv_id":"2309.05475","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-learning-principles-with-a","title":"Implementing Learning Principles with a Personal AI Tutor: A Case Study","date":"2023-09-10","arxiv_id":"2309.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-identify-distinguish-and","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","date":"2023-09-08","arxiv_id":"2309.04635","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-tuning-for-vision","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","date":"2023-09-08","arxiv_id":"2309.04158","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-as-a-recommender-system-a","slug":"evaluating-chatgpt-as-a-recommender-system-a","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","date":"2023-09-07","arxiv_id":"2309.03613","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","n_code_links":2,"syntology":null},{"paper":null,"slug":"flm-101b-an-open-llm-and-how-to-train-it-with","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","date":"2023-09-07","arxiv_id":"2309.03852","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-audio-captioning-via-audibility","slug":"zero-shot-audio-captioning-via-audibility","title":"Zero-Shot Audio Captioning via Audibility Guidance","date":"2023-09-07","arxiv_id":"2309.03884","n_code_links":0,"syntology":null},{"paper":"/paper/hae-rae-bench-evaluation-of-korean-knowledge","slug":"hae-rae-bench-evaluation-of-korean-knowledge","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","date":"2023-09-06","arxiv_id":"2309.02706","n_code_links":1,"syntology":null},{"paper":"/paper/codeapex-a-bilingual-programming-evaluation","slug":"codeapex-a-bilingual-programming-evaluation","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","date":"2023-09-05","arxiv_id":"2309.01940","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-you-trust-chatgpt-perceived-credibility-of","title":"Do You Trust ChatGPT? -- Perceived Credibility of Human and AI-Generated Content","date":"2023-09-05","arxiv_id":"2309.02524","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-androids-dream-of-fictional-references-a","title":"Do androids dream of fictional references? A bibliographic dialogue with ChatGPT3.5","date":"2023-09-04","arxiv_id":"2312.00789","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-or-fine-tuning-a-comparative-study","slug":"prompting-or-fine-tuning-a-comparative-study","title":"Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction","date":"2023-09-04","arxiv_id":"2309.01715","n_code_links":1,"syntology":null},{"paper":"/paper/saturn-an-optimized-data-system-for-large","slug":"saturn-an-optimized-data-system-for-large","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","date":"2023-09-03","arxiv_id":"2309.01226","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-semantic-monitoring","title":"Large Language Models for Semantic Monitoring of Corporate Disclosures: A Case Study on Korea's Top 50 KOSPI Companies","date":"2023-09-01","arxiv_id":"2309.00208","n_code_links":0,"syntology":null},{"paper":"/paper/publicly-shareable-clinical-large-language","slug":"publicly-shareable-clinical-large-language","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","date":"2023-09-01","arxiv_id":"2309.00237","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["starmpcc/asclepius"],"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/taken-out-of-context-on-measuring-situational","slug":"taken-out-of-context-on-measuring-situational","title":"Taken out of context: On measuring situational awareness in LLMs","date":"2023-09-01","arxiv_id":"2309.00667","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"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) · 0 unverified","official":{"repos":["asacooperstickland/situational-awareness-evals"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"why-do-universal-adversarial-attacks-work-on","title":"Why do universal adversarial attacks work on large language models?: Geometry might be the answer","date":"2023-09-01","arxiv_id":"2309.00254","n_code_links":0,"syntology":null},{"paper":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gersteinlab/biocoder"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-has-become-financially-literate-insights","title":"GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice","date":"2023-08-31","arxiv_id":"2309.00649","n_code_links":0,"syntology":null}],"record_sha256":"0e78b1f279cf5f9b06bf974ca3c726979204fd5f4ff92d29c4ad9423dea86583","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}