{"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/20","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":20,"pages_in_order":38,"rows_per_page":100,"rows":[1901,2000],"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/19","next":"/method/linear-warmup-with-cosine-annealing/papers/21","papers":[{"paper":null,"slug":"giellm-japanese-general-information","title":"GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect","date":"2023-11-12","arxiv_id":"2311.06838","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-explain-teaching-large-language-models","title":"Large Language Models are In-context Teachers for Knowledge Reasoning","date":"2023-11-12","arxiv_id":"2311.06985","n_code_links":0,"syntology":null},{"paper":"/paper/data-contamination-quiz-a-tool-to-detect-and","slug":"data-contamination-quiz-a-tool-to-detect-and","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","date":"2023-11-10","arxiv_id":"2311.06233","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":["shahriargolchin/dcq"],"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":"establishing-performance-baselines-in-fine","title":"Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM Users","date":"2023-11-10","arxiv_id":"2311.05903","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-fine-tuning-chatgpt-for-news","title":"Exploring Fine-tuning ChatGPT for News Recommendation","date":"2023-11-10","arxiv_id":"2311.05850","n_code_links":0,"syntology":null},{"paper":"/paper/smart-agent-based-modeling-on-the-use-of","slug":"smart-agent-based-modeling-on-the-use-of","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","date":"2023-11-10","arxiv_id":"2311.06330","n_code_links":4,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["roihn/sabm"],"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":"geoformer-predicting-human-mobility-using","title":"GeoFormer: Predicting Human Mobility using Generative Pre-trained Transformer (GPT)","date":"2023-11-09","arxiv_id":"2311.05092","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-prompt-engineering","title":"Large Language Models and Prompt Engineering for Biomedical Query Focused Multi-Document Summarisation","date":"2023-11-09","arxiv_id":"2311.05169","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-artificial-intelligence-technology","title":"Leveraging Artificial Intelligence Technology for Mapping Research to Sustainable Development Goals: A Case Study","date":"2023-11-09","arxiv_id":"2311.16162","n_code_links":0,"syntology":null},{"paper":"/paper/lumos-learning-agents-with-unified-data","slug":"lumos-learning-agents-with-unified-data","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","date":"2023-11-09","arxiv_id":"2311.05657","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["allenai/lumos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-encoder-decoder-models-for-ai-coaching","slug":"vision-encoder-decoder-models-for-ai-coaching","title":"Vision Encoder-Decoder Models for AI Coaching","date":"2023-11-09","arxiv_id":"2311.16161","n_code_links":2,"syntology":null},{"paper":"/paper/massive-editing-for-large-language-models-via","slug":"massive-editing-for-large-language-models-via","title":"Massive Editing for Large Language Models via Meta Learning","date":"2023-11-08","arxiv_id":"2311.04661","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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chenmientan/malmen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-benchmark-and-contamination-for","slug":"rethinking-benchmark-and-contamination-for","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","date":"2023-11-08","arxiv_id":"2311.04850","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":["lm-sys/llm-decontaminator"],"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":"evaluating-large-language-models-in","title":"Evaluating Large Language Models in Ophthalmology","date":"2023-11-07","arxiv_id":"2311.04933","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-and-mitigating-vulnerabilities-in","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","date":"2023-11-07","arxiv_id":"2311.16153","n_code_links":0,"syntology":null},{"paper":"/paper/locating-cross-task-sequence-continuation","slug":"locating-cross-task-sequence-continuation","title":"Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models","date":"2023-11-07","arxiv_id":"2311.04131","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["apartresearch/seqcont_circuits"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neuro-gpt-developing-a-foundation-model-for","slug":"neuro-gpt-developing-a-foundation-model-for","title":"Neuro-GPT: Towards A Foundation Model for EEG","date":"2023-11-07","arxiv_id":"2311.03764","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":["wenhui0206/neurogpt"],"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/deepinception-hypnotize-large-language-model","slug":"deepinception-hypnotize-large-language-model","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","date":"2023-11-06","arxiv_id":"2311.03191","n_code_links":1,"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":["tmlr-group/deepinception"],"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":"in-context-learning-for-knowledge-base","title":"In-Context Learning for Knowledge Base Question Answering for Unmanned Systems based on Large Language Models","date":"2023-11-06","arxiv_id":"2311.02956","n_code_links":0,"syntology":null},{"paper":"/paper/unraveling-downstream-gender-bias-from-large","slug":"unraveling-downstream-gender-bias-from-large","title":"Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance","date":"2023-11-06","arxiv_id":"2311.03311","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-potential-of-leading-large","title":"Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions","date":"2023-11-05","arxiv_id":"2311.07582","n_code_links":0,"syntology":null},{"paper":"/paper/extraction-of-atypical-aspects-from-customer","slug":"extraction-of-atypical-aspects-from-customer","title":"Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models","date":"2023-11-05","arxiv_id":"2311.02702","n_code_links":2,"syntology":null},{"paper":null,"slug":"uid-as-a-guiding-metric-for-automated","title":"UID as a Guiding Metric for Automated Authorship Obfuscation","date":"2023-11-05","arxiv_id":"2312.03709","n_code_links":0,"syntology":null},{"paper":"/paper/automating-governing-knowledge-commons-and","slug":"automating-governing-knowledge-commons-and","title":"Automating Governing Knowledge Commons and Contextual Integrity (GKC-CI) Privacy Policy Annotations with Large Language Models","date":"2023-11-03","arxiv_id":"2311.02192","n_code_links":1,"syntology":null},{"paper":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-black-box-adversarial-attacks-on","slug":"efficient-black-box-adversarial-attacks-on","title":"Efficient Black-Box Adversarial Attacks on Neural Text Detectors","date":"2023-11-03","arxiv_id":"2311.01873","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-numerical-reasoning","title":"Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data","date":"2023-11-03","arxiv_id":"2311.02216","n_code_links":0,"syntology":null},{"paper":"/paper/long-story-short-a-summarize-then-search","slug":"long-story-short-a-summarize-then-search","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","date":"2023-11-02","arxiv_id":"2311.01233","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-five-accountable-talk-moves-to","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","date":"2023-11-02","arxiv_id":"2311.10749","n_code_links":0,"syntology":null},{"paper":null,"slug":"server-side-rescoring-of-spoken-entity","title":"Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants","date":"2023-11-02","arxiv_id":"2311.01398","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-reliable-judges-a","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","date":"2023-11-01","arxiv_id":"2311.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-training-and-fine-tuning-for","title":"Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering","date":"2023-11-01","arxiv_id":"2311.00204","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-powerful-enough-to-analyze-the","title":"Is GPT Powerful Enough to Analyze the Emotions of Memes?","date":"2023-11-01","arxiv_id":"2311.00223","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-lexical-simplification-with","slug":"unsupervised-lexical-simplification-with","title":"Unsupervised Lexical Simplification with Context Augmentation","date":"2023-11-01","arxiv_id":"2311.00310","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-large-language-models-solve-verbal","title":"Do large language models solve verbal analogies like children do?","date":"2023-10-31","arxiv_id":"2310.20384","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-gpt-4-pass-the-turing-test","title":"Does GPT-4 pass the Turing test?","date":"2023-10-31","arxiv_id":"2310.20216","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-classification-of-student-help","title":"Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models","date":"2023-10-31","arxiv_id":"2310.20105","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-multi-fidelity-learning-for-cost","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","date":"2023-10-31","arxiv_id":"2310.20153","n_code_links":0,"syntology":null},{"paper":"/paper/psycot-psychological-questionnaire-as","slug":"psycot-psychological-questionnaire-as","title":"PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection","date":"2023-10-31","arxiv_id":"2310.20256","n_code_links":1,"syntology":null},{"paper":null,"slug":"theory-of-mind-in-large-language-models","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","date":"2023-10-31","arxiv_id":"2310.20320","n_code_links":0,"syntology":null},{"paper":null,"slug":"herd-using-multiple-smaller-llms-to-match-the","title":"Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer","date":"2023-10-30","arxiv_id":"2310.19902","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-by-design-text-classification","slug":"interpretable-by-design-text-classification","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","date":"2023-10-30","arxiv_id":"2310.19660","n_code_links":1,"syntology":null},{"paper":"/paper/litcab-lightweight-calibration-of-language","slug":"litcab-lightweight-calibration-of-language","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","date":"2023-10-30","arxiv_id":"2310.19208","n_code_links":1,"syntology":null},{"paper":null,"slug":"remember-what-you-did-so-you-know-what-to-do","title":"Remember what you did so you know what to do next","date":"2023-10-30","arxiv_id":"2311.01468","n_code_links":0,"syntology":null},{"paper":"/paper/synthetic-imitation-edit-feedback-for-factual","slug":"synthetic-imitation-edit-feedback-for-factual","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","date":"2023-10-30","arxiv_id":"2310.20033","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 3 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":["seasonyao/learnfromhumanedit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/eticor-corpus-for-analyzing-llms-for","slug":"eticor-corpus-for-analyzing-llms-for","title":"EtiCor: Corpus for Analyzing LLMs for Etiquettes","date":"2023-10-29","arxiv_id":"2310.18974","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-chatbots-to-phishbots-preventing","title":"From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude","date":"2023-10-29","arxiv_id":"2310.19181","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-kernel-surrogates-for-neural","title":"Efficient kernel surrogates for neural network-based regression","date":"2023-10-28","arxiv_id":"2310.18612","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-synergy-of-speculative-decoding-and","title":"The Synergy of Speculative Decoding and Batching in Serving Large Language Models","date":"2023-10-28","arxiv_id":"2310.18813","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-aspect-based","slug":"large-language-models-for-aspect-based","title":"Large language models for aspect-based sentiment analysis","date":"2023-10-27","arxiv_id":"2310.18025","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":["qagentur/absa_llm"],"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/lost-in-translation-found-in-spans","slug":"lost-in-translation-found-in-spans","title":"Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media","date":"2023-10-27","arxiv_id":"2310.18205","n_code_links":1,"syntology":null},{"paper":"/paper/offmix-3l-a-novel-code-mixed-dataset-in","slug":"offmix-3l-a-novel-code-mixed-dataset-in","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","date":"2023-10-27","arxiv_id":"2310.18387","n_code_links":1,"syntology":null},{"paper":"/paper/sentmix-3l-a-bangla-english-hindi-code-mixed","slug":"sentmix-3l-a-bangla-english-hindi-code-mixed","title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","date":"2023-10-27","arxiv_id":"2310.18023","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-grade-short-answer-reading","title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","date":"2023-10-26","arxiv_id":"2310.18373","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedpeat-convergence-of-federated-learning","title":"FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing","date":"2023-10-26","arxiv_id":"2310.17491","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-transcripts-to-insights-uncovering","title":"From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI","date":"2023-10-26","arxiv_id":"2310.17721","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-learning-dynamics-with-random","slug":"in-context-learning-dynamics-with-random","title":"In-Context Learning Dynamics with Random Binary Sequences","date":"2023-10-26","arxiv_id":"2310.17639","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"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) · 0 unverified","official":{"repos":["ebigelow/icl-random-binary"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightlm-a-lightweight-deep-and-narrow","slug":"lightlm-a-lightweight-deep-and-narrow","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","date":"2023-10-26","arxiv_id":"2310.17488","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongyuanjushi/lightlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mo-yolo-end-to-end-multiple-object-tracking","title":"DecoderTracker: Decoder-Only Method for Multiple-Object Tracking","date":"2023-10-26","arxiv_id":"2310.17170","n_code_links":0,"syntology":null},{"paper":"/paper/sliceformer-make-multi-head-attention-as","slug":"sliceformer-make-multi-head-attention-as","title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","date":"2023-10-26","arxiv_id":"2310.17683","n_code_links":1,"syntology":null},{"paper":null,"slug":"you-are-an-expert-linguistic-annotator-limits","title":"\"You Are An Expert Linguistic Annotator\": Limits of LLMs as Analyzers of Abstract Meaning Representation","date":"2023-10-26","arxiv_id":"2310.17793","n_code_links":0,"syntology":null},{"paper":null,"slug":"zeroquant-hero-hardware-enhanced-robust","title":"ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers","date":"2023-10-26","arxiv_id":"2310.17723","n_code_links":0,"syntology":null},{"paper":"/paper/babystories-can-reinforcement-learning-teach","slug":"babystories-can-reinforcement-learning-teach","title":"BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?","date":"2023-10-25","arxiv_id":"2310.16681","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["zephyr1022/babystories-utsa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"boost-harnessing-black-box-control-to-boost","title":"BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation","date":"2023-10-25","arxiv_id":"2310.17054","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-models-follow-human-summarization","title":"Can GPT models Follow Human Summarization Guidelines? Evaluating ChatGPT and GPT-4 for Dialogue Summarization","date":"2023-10-25","arxiv_id":"2310.16810","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-stumpers-large-language-models-vs","title":"Decoding Stumpers: Large Language Models vs. Human Problem-Solvers","date":"2023-10-25","arxiv_id":"2310.16411","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-diffusion-language-modeling-by","slug":"discrete-diffusion-language-modeling-by","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","date":"2023-10-25","arxiv_id":"2310.16834","n_code_links":4,"syntology":{"ran":16,"of":18,"n_ran_checked":14,"n_instrument":2,"unverified":2,"pointer_only":15,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["louaaron/score-entropy-discrete-diffusion"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-well-can-machine-generated-texts-be","title":"How well can machine-generated texts be identified and can language models be trained to avoid identification?","date":"2023-10-25","arxiv_id":"2310.16992","n_code_links":0,"syntology":null},{"paper":null,"slug":"muslim-violence-bias-persists-in-debiased-gpt","title":"Muslim-Violence Bias Persists in Debiased GPT Models","date":"2023-10-25","arxiv_id":"2310.18368","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-3-prompting-review-rephrase-and-resolve-for","title":"R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context","date":"2023-10-25","arxiv_id":"2310.16535","n_code_links":0,"syntology":null},{"paper":null,"slug":"rcagent-cloud-root-cause-analysis-by","title":"RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models","date":"2023-10-25","arxiv_id":"2310.16340","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-communication-theory-perspective-on","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","date":"2023-10-24","arxiv_id":"2310.18358","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-language-model-with-limited-memory-capacity","title":"A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing","date":"2023-10-24","arxiv_id":"2310.16142","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-enhanced-auto-correction-of-programming","title":"AI-enhanced Auto-correction of Programming Exercises: How Effective is GPT-3.5?","date":"2023-10-24","arxiv_id":"2311.10737","n_code_links":0,"syntology":null},{"paper":"/paper/background-summarization-of-event-timelines","slug":"background-summarization-of-event-timelines","title":"Background Summarization of Event Timelines","date":"2023-10-24","arxiv_id":"2310.16197","n_code_links":1,"syntology":null},{"paper":null,"slug":"dissecting-in-context-learning-of","title":"Dissecting In-Context Learning of Translations in GPTs","date":"2023-10-24","arxiv_id":"2310.15987","n_code_links":0,"syntology":null},{"paper":"/paper/fighting-fire-with-fire-the-dual-role-of-llms","slug":"fighting-fire-with-fire-the-dual-role-of-llms","title":"Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation","date":"2023-10-24","arxiv_id":"2310.15515","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-free-text-human-feedback","slug":"learning-from-free-text-human-feedback","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","date":"2023-10-24","arxiv_id":"2310.15758","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 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) · 1 unverified","official":{"repos":["ukplab/emnlp2023-learning-from-free-text-human-feedback"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-janus-interface-how-fine-tuning-in-large","slug":"the-janus-interface-how-fine-tuning-in-large","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","date":"2023-10-24","arxiv_id":"2310.15469","n_code_links":1,"syntology":null},{"paper":"/paper/trams-training-free-memory-selection-for-long","slug":"trams-training-free-memory-selection-for-long","title":"TRAMS: Training-free Memory Selection for Long-range Language Modeling","date":"2023-10-24","arxiv_id":"2310.15494","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":["lwaekfjlk/trams"],"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":"what-makes-it-ok-to-set-a-fire-iterative-self","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","date":"2023-10-24","arxiv_id":"2310.15431","n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-inference-using-llm-guided-discovery","title":"Causal Inference Using LLM-Guided Discovery","date":"2023-10-23","arxiv_id":"2310.15117","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-spatial-understanding-of-large","slug":"evaluating-spatial-understanding-of-large","title":"Evaluating Spatial Understanding of Large Language Models","date":"2023-10-23","arxiv_id":"2310.14540","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["runopti/spatialevalllm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-knowledge-base-completion","title":"Evaluating the Knowledge Base Completion Potential of GPT","date":"2023-10-23","arxiv_id":"2310.14771","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-1","title":"Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering","date":"2023-10-23","arxiv_id":"2310.14602","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-as-an-effective-zero-shot-evaluator-for","title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions","date":"2023-10-23","arxiv_id":"2310.15405","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructexcel-a-benchmark-for-natural","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","date":"2023-10-23","arxiv_id":"2310.14495","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-hallucinate-but-may-excel-at","slug":"language-models-hallucinate-but-may-excel-at","title":"Language Models Hallucinate, but May Excel at Fact Verification","date":"2023-10-23","arxiv_id":"2310.14564","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jianguanthu/llmforfv"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/linc-a-neurosymbolic-approach-for-logical","slug":"linc-a-neurosymbolic-approach-for-logical","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","date":"2023-10-23","arxiv_id":"2310.15164","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":0,"n_instrument":1,"unverified":6,"pointer_only":7,"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) · 6 unverified","official":{"repos":["benlipkin/linc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm-in-the-loop-leveraging-large-language","slug":"llm-in-the-loop-leveraging-large-language","title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","date":"2023-10-23","arxiv_id":"2310.15100","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sjdai/llm-thematic-analysis"],"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":"prefix-tuning-based-unsupervised-text-style","title":"Prefix-Tuning Based Unsupervised Text Style Transfer","date":"2023-10-23","arxiv_id":"2310.14599","n_code_links":0,"syntology":null},{"paper":"/paper/teleqna-a-benchmark-dataset-to-assess-large","slug":"teleqna-a-benchmark-dataset-to-assess-large","title":"TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge","date":"2023-10-23","arxiv_id":"2310.15051","n_code_links":1,"syntology":null},{"paper":"/paper/the-continued-usefulness-of-vocabulary-tests","slug":"the-continued-usefulness-of-vocabulary-tests","title":"Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models","date":"2023-10-23","arxiv_id":"2310.14703","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-mechanistic-interpretation-of-multi","slug":"towards-a-mechanistic-interpretation-of-multi","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","date":"2023-10-23","arxiv_id":"2310.14491","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yifan-h/mechanisticprobe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-language-models-laugh-at-youtube-short","slug":"can-language-models-laugh-at-youtube-short","title":"Can Language Models Laugh at YouTube Short-form Videos?","date":"2023-10-22","arxiv_id":"2310.14159","n_code_links":1,"syntology":null},{"paper":"/paper/is-chatgpt-a-game-changer-for-geocoding-a","slug":"is-chatgpt-a-game-changer-for-geocoding-a","title":"Is ChatGPT a game changer for geocoding -- a benchmark for geocoding address parsing techniques","date":"2023-10-22","arxiv_id":"2310.14360","n_code_links":1,"syntology":null},{"paper":"/paper/text-generation-for-dataset-augmentation-in","slug":"text-generation-for-dataset-augmentation-in","title":"Text generation for dataset augmentation in security classification tasks","date":"2023-10-22","arxiv_id":"2310.14429","n_code_links":1,"syntology":null},{"paper":"/paper/gemba-mqm-detecting-translation-quality-error","slug":"gemba-mqm-detecting-translation-quality-error","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","date":"2023-10-21","arxiv_id":"2310.13988","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"haterephrase-zero-and-few-shot-reduction-of","title":"HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models","date":"2023-10-21","arxiv_id":"2310.13985","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-baseline-for-knowledge-based-visual","slug":"a-simple-baseline-for-knowledge-based-visual","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","date":"2023-10-20","arxiv_id":"2310.13570","n_code_links":0,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":null}}],"record_sha256":"49dd8461180c78bae7b095cc1b3b470f7b8f04376a43a04dd4805fb9eddb9f59","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}