{"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/14","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":14,"pages_in_order":40,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/method/cosine-annealing/papers/15","papers":[{"paper":"/paper/the-instruction-hierarchy-training-llms-to","slug":"the-instruction-hierarchy-training-llms-to","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","date":"2024-04-19","arxiv_id":"2404.13208","n_code_links":1,"syntology":null},{"paper":null,"slug":"augmenting-emotion-features-in-irony","title":"Augmenting emotion features in irony detection with Large language modeling","date":"2024-04-18","arxiv_id":"2404.12291","n_code_links":0,"syntology":null},{"paper":"/paper/from-form-s-to-meaning-probing-the-semantic","slug":"from-form-s-to-meaning-probing-the-semantic","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","date":"2024-04-18","arxiv_id":"2404.12145","n_code_links":1,"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":["facebookresearch/multisense_consistency"],"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":"midget-music-conditioned-3d-dance-generation","title":"MIDGET: Music Conditioned 3D Dance Generation","date":"2024-04-18","arxiv_id":"2404.12062","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-analysis-of-deep-natural-networks","slug":"comparative-analysis-of-deep-natural-networks","title":"Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/aesexpert-towards-multi-modality-foundation","slug":"aesexpert-towards-multi-modality-foundation","title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception","date":"2024-04-15","arxiv_id":"2404.09624","n_code_links":1,"syntology":null},{"paper":null,"slug":"deceiving-to-enlighten-coaxing-llms-to-self","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","date":"2024-04-15","arxiv_id":"2404.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"quality-assessment-of-prompts-used-in-code","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","date":"2024-04-15","arxiv_id":"2404.10155","n_code_links":0,"syntology":null},{"paper":"/paper/s-gpts-a-new-approach-to-autoregressive","slug":"s-gpts-a-new-approach-to-autoregressive","title":"σ-GPTs: A New Approach to Autoregressive Models","date":"2024-04-15","arxiv_id":"2404.09562","n_code_links":1,"syntology":null},{"paper":null,"slug":"creativeval-evaluating-creativity-of-llm","title":"CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation","date":"2024-04-12","arxiv_id":"2404.08806","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-chatgpt-transforming-academics-writing","title":"Is ChatGPT Transforming Academics' Writing Style?","date":"2024-04-12","arxiv_id":"2404.08627","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-small-base-lms-with-fewer-tokens","slug":"pre-training-small-base-lms-with-fewer-tokens","title":"Inheritune: Training Smaller Yet More Attentive Language Models","date":"2024-04-12","arxiv_id":"2404.08634","n_code_links":1,"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: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sanyalsunny111/llm-inheritune"],"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":"revisiting-code-similarity-evaluation-with","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","date":"2024-04-12","arxiv_id":"2404.08817","n_code_links":0,"syntology":null},{"paper":"/paper/small-models-are-still-effective-cross-domain","slug":"small-models-are-still-effective-cross-domain","title":"Small Models Are (Still) Effective Cross-Domain Argument Extractors","date":"2024-04-12","arxiv_id":"2404.08579","n_code_links":1,"syntology":null},{"paper":"/paper/amplegcg-learning-a-universal-and","slug":"amplegcg-learning-a-universal-and","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","date":"2024-04-11","arxiv_id":"2404.07921","n_code_links":1,"syntology":null},{"paper":"/paper/on-training-data-influence-of-gpt-models","slug":"on-training-data-influence-of-gpt-models","title":"On Training Data Influence of GPT Models","date":"2024-04-11","arxiv_id":"2404.07840","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["eleutherai/pythia","ernie-research/gptfluence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rumour-evaluation-with-very-large-language","slug":"rumour-evaluation-with-very-large-language","title":"Rumour Evaluation with Very Large Language Models","date":"2024-04-11","arxiv_id":"2404.16859","n_code_links":1,"syntology":null},{"paper":"/paper/simpler-becomes-harder-do-llms-exhibit-a","slug":"simpler-becomes-harder-do-llms-exhibit-a","title":"Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora?","date":"2024-04-10","arxiv_id":"2404.06838","n_code_links":1,"syntology":null},{"paper":"/paper/all-in-one-an-empirical-study-of-gpt-for-few","slug":"all-in-one-an-empirical-study-of-gpt-for-few","title":"Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis","date":"2024-04-09","arxiv_id":"2404.06063","n_code_links":1,"syntology":null},{"paper":null,"slug":"characterizing-multimodal-long-form","title":"Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports","date":"2024-04-09","arxiv_id":"2404.06162","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-potential-of-large-foundation","slug":"exploring-the-potential-of-large-foundation","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","date":"2024-04-09","arxiv_id":"2404.06194","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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":["ltttpku/cmd-se-release"],"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":null,"slug":"generative-pre-trained-transformer-for-2","title":"Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning","date":"2024-04-09","arxiv_id":"2404.06330","n_code_links":0,"syntology":null},{"paper":null,"slug":"sandwich-attack-multi-language-mixture","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","date":"2024-04-09","arxiv_id":"2404.07242","n_code_links":0,"syntology":null},{"paper":null,"slug":"constraining-large-language-model-for","title":"Guiding Large Language Models to Generate Computer-Parsable Content","date":"2024-04-08","arxiv_id":"2404.05499","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-interventional-reasoning","title":"Evaluating Interventional Reasoning Capabilities of Large Language Models","date":"2024-04-08","arxiv_id":"2404.05545","n_code_links":0,"syntology":null},{"paper":null,"slug":"ltner-large-language-model-tagging-for-named","title":"LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity Marking","date":"2024-04-08","arxiv_id":"2404.05624","n_code_links":0,"syntology":null},{"paper":"/paper/petkaz-at-semeval-2024-task-3-advancing","slug":"petkaz-at-semeval-2024-task-3-advancing","title":"PetKaz at SemEval-2024 Task 3: Advancing Emotion Classification with an LLM for Emotion-Cause Pair Extraction in Conversations","date":"2024-04-08","arxiv_id":"2404.05502","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-of-language-models-part-3-3-knowledge","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","date":"2024-04-08","arxiv_id":"2404.05405","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-extraction-using-large-language","title":"Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations","date":"2024-04-08","arxiv_id":"2404.05415","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-level-framework-for-accelerating","slug":"a-multi-level-framework-for-accelerating","title":"A Multi-Level Framework for Accelerating Training Transformer Models","date":"2024-04-07","arxiv_id":"2404.07999","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["photooon/multi-level-training-framework"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/iitk-at-semeval-2024-task-2-exploring-the","slug":"iitk-at-semeval-2024-task-2-exploring-the","title":"IITK at SemEval-2024 Task 2: Exploring the Capabilities of LLMs for Safe Biomedical Natural Language Inference for Clinical Trials","date":"2024-04-06","arxiv_id":"2404.04510","n_code_links":1,"syntology":null},{"paper":null,"slug":"recgpt-generative-personalized-prompts-for","title":"RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm","date":"2024-04-06","arxiv_id":"2404.08675","n_code_links":0,"syntology":null},{"paper":"/paper/scope-ambiguities-in-large-language-models","slug":"scope-ambiguities-in-large-language-models","title":"Scope Ambiguities in Large Language Models","date":"2024-04-05","arxiv_id":"2404.04332","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-large-language-models-rank-fairly-an","title":"Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers","date":"2024-04-04","arxiv_id":"2404.03192","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-at-uc-santa-cruz-at-semeval-2024-task-5","slug":"nlp-at-uc-santa-cruz-at-semeval-2024-task-5","title":"NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA","date":"2024-04-04","arxiv_id":"2404.03150","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-tutoring-in-software-engineering-education","title":"AI-Tutoring in Software Engineering Education","date":"2024-04-03","arxiv_id":"2404.02548","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-incomplete-loop-deductive-inductive-and","title":"An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models","date":"2024-04-03","arxiv_id":"2404.03028","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-large-language-models-for-2","slug":"benchmarking-large-language-models-for-2","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","date":"2024-04-03","arxiv_id":"2404.02403","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-detox-an-in-context-learning-based","title":"GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification","date":"2024-04-03","arxiv_id":"2404.03052","n_code_links":0,"syntology":null},{"paper":"/paper/utebc-nlp-at-semeval-2024-task-9-can-llms-be","slug":"utebc-nlp-at-semeval-2024-task-9-can-llms-be","title":"uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?","date":"2024-04-03","arxiv_id":"2404.02474","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":["ipouyall/can-llms-be-lateral-thinkers"],"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/advancing-llm-reasoning-generalists-with","slug":"advancing-llm-reasoning-generalists-with","title":"Advancing LLM Reasoning Generalists with Preference Trees","date":"2024-04-02","arxiv_id":"2404.02078","n_code_links":1,"syntology":{"ran":18,"of":20,"n_ran_checked":13,"n_instrument":5,"unverified":2,"pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["openbmb/eurus"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"auditing-large-language-models-for-enhanced","title":"Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approach","date":"2024-04-02","arxiv_id":"2404.01768","n_code_links":0,"syntology":null},{"paper":"/paper/cmat-a-multi-agent-collaboration-tuning","slug":"cmat-a-multi-agent-collaboration-tuning","title":"CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models","date":"2024-04-02","arxiv_id":"2404.01663","n_code_links":1,"syntology":null},{"paper":"/paper/collapse-of-self-trained-language-models","slug":"collapse-of-self-trained-language-models","title":"Collapse of Self-trained Language Models","date":"2024-04-02","arxiv_id":"2404.02305","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["davidherel/collapse-lm-iclr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"comparative-study-of-domain-driven-terms","title":"Comparative Study of Domain Driven Terms Extraction Using Large Language Models","date":"2024-04-02","arxiv_id":"2404.02330","n_code_links":0,"syntology":null},{"paper":"/paper/deconstructing-in-context-learning","slug":"deconstructing-in-context-learning","title":"Deconstructing In-Context Learning: Understanding Prompts via Corruption","date":"2024-04-02","arxiv_id":"2404.02054","n_code_links":1,"syntology":null},{"paper":"/paper/jailbreaking-leading-safety-aligned-llms-with","slug":"jailbreaking-leading-safety-aligned-llms-with","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","date":"2024-04-02","arxiv_id":"2404.02151","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/llm-adaptive-attacks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metal-towards-multilingual-meta-evaluation","title":"METAL: Towards Multilingual Meta-Evaluation","date":"2024-04-02","arxiv_id":"2404.01667","n_code_links":0,"syntology":null},{"paper":"/paper/scene-adaptive-sparse-transformer-for-event","slug":"scene-adaptive-sparse-transformer-for-event","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","date":"2024-04-02","arxiv_id":"2404.01882","n_code_links":1,"syntology":{"ran":19,"of":23,"n_ran_checked":19,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["peterande/sast"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/sgsh-stimulate-large-language-models-with","slug":"sgsh-stimulate-large-language-models-with","title":"SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation","date":"2024-04-02","arxiv_id":"2404.01923","n_code_links":1,"syntology":null},{"paper":"/paper/toward-informal-language-processing-knowledge","slug":"toward-informal-language-processing-knowledge","title":"Toward Informal Language Processing: Knowledge of Slang in Large Language Models","date":"2024-04-02","arxiv_id":"2404.02323","n_code_links":1,"syntology":null},{"paper":null,"slug":"artificial-intelligence-and-the-spatial","title":"Artificial Intelligence and the Spatial Documentation of Languages","date":"2024-04-01","arxiv_id":"2404.01263","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-enhanced-retrieval-tool-for-homework","title":"BERT-Enhanced Retrieval Tool for Homework Plagiarism Detection System","date":"2024-04-01","arxiv_id":"2404.01582","n_code_links":0,"syntology":null},{"paper":"/paper/fables-evaluating-faithfulness-and-content","slug":"fables-evaluating-faithfulness-and-content","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","date":"2024-04-01","arxiv_id":"2404.01261","n_code_links":3,"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":["mungg/fables"],"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/unveiling-divergent-inductive-biases-of-llms","slug":"unveiling-divergent-inductive-biases-of-llms","title":"Unveiling Divergent Inductive Biases of LLMs on Temporal Data","date":"2024-04-01","arxiv_id":"2404.01453","n_code_links":1,"syntology":null},{"paper":"/paper/chops-chat-with-customer-profile-systems-for","slug":"chops-chat-with-customer-profile-systems-for","title":"CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs","date":"2024-03-31","arxiv_id":"2404.01343","n_code_links":1,"syntology":null},{"paper":"/paper/couda-coherence-evaluation-via-unified-data","slug":"couda-coherence-evaluation-via-unified-data","title":"CoUDA: Coherence Evaluation via Unified Data Augmentation","date":"2024-03-31","arxiv_id":"2404.00681","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-free-semantic-segmentation-via-llm","title":"Training-Free Semantic Segmentation via LLM-Supervision","date":"2024-03-31","arxiv_id":"2404.00701","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-on-nlp-data","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","date":"2024-03-30","arxiv_id":"2404.00303","n_code_links":0,"syntology":null},{"paper":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-v-s-media-bias-a-comparative-study-of","title":"ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models","date":"2024-03-29","arxiv_id":"2403.20158","n_code_links":0,"syntology":null},{"paper":null,"slug":"dataagent-evaluating-large-language-models","title":"DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries","date":"2024-03-29","arxiv_id":"2404.00188","n_code_links":0,"syntology":null},{"paper":null,"slug":"realm-reference-resolution-as-language","title":"ReALM: Reference Resolution As Language Modeling","date":"2024-03-29","arxiv_id":"2403.20329","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-review-of-multi-modal-large-language-and","title":"A Review of Multi-Modal Large Language and Vision Models","date":"2024-03-28","arxiv_id":"2404.01322","n_code_links":0,"syntology":null},{"paper":null,"slug":"factoid-factual-entailment-for-hallucination","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","date":"2024-03-28","arxiv_id":"2403.19113","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-retrieve-conversational","title":"Generating Multi-Aspect Queries for Conversational Search","date":"2024-03-28","arxiv_id":"2403.19302","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-key-mechanisms-of-factual-recall","slug":"interpreting-key-mechanisms-of-factual-recall","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","date":"2024-03-28","arxiv_id":"2403.19521","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["trestad/factual-recall-mechanism"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"just-dna-seq-open-source-personal-genomics","title":"Just-DNA-Seq, open-source personal genomics platform: longevity science for everyone","date":"2024-03-28","arxiv_id":"2403.19087","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-from","title":"A Survey on Large Language Models from Concept to Implementation","date":"2024-03-27","arxiv_id":"2403.18969","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-for-health-1","title":"Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data","date":"2024-03-27","arxiv_id":"2403.19031","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-in-hci-data-work-bridging-the-gap","title":"LLMs in HCI Data Work: Bridging the Gap Between Information Retrieval and Responsible Research Practices","date":"2024-03-27","arxiv_id":"2403.18173","n_code_links":0,"syntology":null},{"paper":"/paper/long-form-factuality-in-large-language-models","slug":"long-form-factuality-in-large-language-models","title":"Long-form factuality in large language models","date":"2024-03-27","arxiv_id":"2403.18802","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/long-form-factuality"],"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":["listed","official"]}}},{"paper":"/paper/parco-part-coordinating-text-to-motion","slug":"parco-part-coordinating-text-to-motion","title":"ParCo: Part-Coordinating Text-to-Motion Synthesis","date":"2024-03-27","arxiv_id":"2403.18512","n_code_links":1,"syntology":null},{"paper":"/paper/reshaping-free-text-radiology-notes-into","slug":"reshaping-free-text-radiology-notes-into","title":"Reshaping Free-Text Radiology Notes Into Structured Reports With Generative Transformers","date":"2024-03-27","arxiv_id":"2403.18938","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-detection-with-code-language","slug":"vulnerability-detection-with-code-language","title":"Vulnerability Detection with Code Language Models: How Far Are We?","date":"2024-03-27","arxiv_id":"2403.18624","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["dlvuldet/primevul"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decoding-probing-revealing-internal","title":"Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs","date":"2024-03-26","arxiv_id":"2403.17299","n_code_links":0,"syntology":null},{"paper":null,"slug":"disambiguate-entity-matching-through-relation","title":"Disambiguate Entity Matching using Large Language Models through Relation Discovery","date":"2024-03-26","arxiv_id":"2403.17344","n_code_links":0,"syntology":null},{"paper":"/paper/don-t-trust-verify-grounding-llm-quantitative","slug":"don-t-trust-verify-grounding-llm-quantitative","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","date":"2024-03-26","arxiv_id":"2403.18120","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":2,"n_instrument":8,"unverified":2,"pointer_only":0,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jinpz/dtv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/ellen-extremely-lightly-supervised-learning","slug":"ellen-extremely-lightly-supervised-learning","title":"ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition","date":"2024-03-26","arxiv_id":"2403.17385","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-legal-document-retrieval-a-multi","title":"Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models","date":"2024-03-26","arxiv_id":"2403.18093","n_code_links":0,"syntology":null},{"paper":null,"slug":"magis-llm-based-multi-agent-framework-for","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","date":"2024-03-26","arxiv_id":"2403.17927","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-all-similarities-are-created-equal","title":"Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes","date":"2024-03-26","arxiv_id":"2403.17691","n_code_links":0,"syntology":null},{"paper":"/paper/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/targeted-visualization-of-the-backbone-of","slug":"targeted-visualization-of-the-backbone-of","title":"Targeted Visualization of the Backbone of Encoder LLMs","date":"2024-03-26","arxiv_id":"2403.18872","n_code_links":1,"syntology":null},{"paper":null,"slug":"verbing-weirds-language-models-evaluation-of","title":"Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs","date":"2024-03-26","arxiv_id":"2403.17856","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparison-of-human-gpt-3-5-and-gpt-4","slug":"a-comparison-of-human-gpt-3-5-and-gpt-4","title":"A comparison of Human, GPT-3.5, and GPT-4 Performance in a University-Level Coding Course","date":"2024-03-25","arxiv_id":"2403.16977","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-refinement-of-project-level-code","slug":"iterative-refinement-of-project-level-code","title":"Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback","date":"2024-03-25","arxiv_id":"2403.16792","n_code_links":1,"syntology":null},{"paper":"/paper/repairagent-an-autonomous-llm-based-agent-for","slug":"repairagent-an-autonomous-llm-based-agent-for","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","date":"2024-03-25","arxiv_id":"2403.17134","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sola-st/RepairAgent"],"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":"/paper/textit-linkprompt-natural-and-universal","slug":"textit-linkprompt-natural-and-universal","title":"$\\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models","date":"2024-03-25","arxiv_id":"2403.16432","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":["savannahxu79/linkprompt"],"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/towards-algorithmic-fidelity-mental-health","slug":"towards-algorithmic-fidelity-mental-health","title":"Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data","date":"2024-03-25","arxiv_id":"2403.16909","n_code_links":1,"syntology":null},{"paper":"/paper/smtf-sparse-transformer-with-multiscale","slug":"smtf-sparse-transformer-with-multiscale","title":"SMTF: Sparse transformer with multiscale contextual fusion for medical image segmentation","date":"2024-03-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sql-encoder-improving-nl2sql-in-context","title":"SQL-Encoder: Improving NL2SQL In-Context Learning Through a Context-Aware Encoder","date":"2024-03-24","arxiv_id":"2403.16204","n_code_links":0,"syntology":null},{"paper":null,"slug":"codeshell-technical-report","title":"CodeShell Technical Report","date":"2024-03-23","arxiv_id":"2403.15747","n_code_links":0,"syntology":null},{"paper":null,"slug":"contact-aware-human-motion-generation-from","title":"Contact-aware Human Motion Generation from Textual Descriptions","date":"2024-03-23","arxiv_id":"2403.15709","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-ontoclean","title":"Using Large Language Models for OntoClean-based Ontology Refinement","date":"2024-03-23","arxiv_id":"2403.15864","n_code_links":0,"syntology":null},{"paper":"/paper/when-llm-based-code-generation-meets-the","slug":"when-llm-based-code-generation-meets-the","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","date":"2024-03-23","arxiv_id":"2403.15852","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapprox-adaptive-approximation-in-adam","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","date":"2024-03-22","arxiv_id":"2403.14958","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-explore-in-context","title":"Can large language models explore in-context?","date":"2024-03-22","arxiv_id":"2403.15371","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-evaluation-and-insights-into-1","slug":"comprehensive-evaluation-and-insights-into-1","title":"Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation","date":"2024-03-22","arxiv_id":"2403.14965","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-gender-and-racial-biases-in-large","title":"Measuring Gender and Racial Biases in Large Language Models","date":"2024-03-22","arxiv_id":"2403.15281","n_code_links":0,"syntology":null}],"record_sha256":"b8651fe76b011abaa10cf12062af3d0de1be880666ab39e518abc652949a9603","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}