{"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/11","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":11,"pages_in_order":40,"rows_per_page":100,"rows":[1001,1100],"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/10","next":"/method/cosine-annealing/papers/12","papers":[{"paper":null,"slug":"plagbench-exploring-the-duality-of-large","title":"PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection","date":"2024-06-24","arxiv_id":"2406.16288","n_code_links":0,"syntology":null},{"paper":"/paper/the-gpt-writingprompts-dataset-a-comparative","slug":"the-gpt-writingprompts-dataset-a-comparative","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","date":"2024-06-24","arxiv_id":"2406.16767","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-graph-based-cross-document","slug":"towards-better-graph-based-cross-document","title":"Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing","date":"2024-06-24","arxiv_id":"2406.16529","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-the","title":"Evaluating the Effectiveness of the Foundational Models for Q&A Classification in Mental Health care","date":"2024-06-23","arxiv_id":"2406.15966","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval2000-benchmarking-and-improving","title":"GraphEval2000: Benchmarking and Improving Large Language Models on Graph Datasets","date":"2024-06-23","arxiv_id":"2406.16176","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-visualizations-with","title":"Can LLMs Generate Visualizations with Dataless Prompts?","date":"2024-06-22","arxiv_id":"2406.17805","n_code_links":0,"syntology":null},{"paper":"/paper/ss-bench-a-benchmark-for-social-story","slug":"ss-bench-a-benchmark-for-social-story","title":"SS-GEN: A Social Story Generation Framework with Large Language Models","date":"2024-06-22","arxiv_id":"2406.15695","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-gpt-based-code-review-system-for","title":"A GPT-based Code Review System for Programming Language Learning","date":"2024-06-21","arxiv_id":"2407.04722","n_code_links":0,"syntology":null},{"paper":null,"slug":"anime-popularity-prediction-before-huge","title":"Anime Popularity Prediction Before Huge Investments: a Multimodal Approach Using Deep Learning","date":"2024-06-21","arxiv_id":"2406.16961","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-as-research-scientist-probing-gpt-s","title":"ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor","date":"2024-06-20","arxiv_id":"2406.14765","n_code_links":0,"syntology":null},{"paper":null,"slug":"cryptogpt-a-7b-model-rivaling-gpt-4-in-the","title":"CryptoGPT: a 7B model rivaling GPT-4 in the task of analyzing and classifying real-time financial news","date":"2024-06-20","arxiv_id":"2406.14039","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-implicit-bias-in-large-language","slug":"evaluating-implicit-bias-in-large-language","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","date":"2024-06-20","arxiv_id":"2406.14023","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-ai-for-enhancing-active-learning","title":"Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questions","date":"2024-06-20","arxiv_id":"2406.13903","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-compute-the-probability-of-a-word","slug":"how-to-compute-the-probability-of-a-word","title":"How to Compute the Probability of a Word","date":"2024-06-20","arxiv_id":"2406.14561","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 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":["tpimentelms/probability-of-a-word"],"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":"identifying-user-goals-from-ui-trajectories","title":"Identifying User Goals from UI Trajectories","date":"2024-06-20","arxiv_id":"2406.14314","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-plan-for-retrieval-augmented","slug":"learning-to-plan-for-retrieval-augmented","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","date":"2024-06-20","arxiv_id":"2406.14282","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":["zjukg/lpkg"],"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/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/persuasiveness-of-generated-free-text","slug":"persuasiveness-of-generated-free-text","title":"Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking","date":"2024-06-20","arxiv_id":"2406.13905","n_code_links":1,"syntology":null},{"paper":"/paper/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scidmt-a-large-scale-corpus-for-detecting","title":"SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions","date":"2024-06-20","arxiv_id":"2406.14756","n_code_links":0,"syntology":null},{"paper":"/paper/on-ai-inspired-ui-design","slug":"on-ai-inspired-ui-design","title":"On AI-Inspired UI-Design","date":"2024-06-19","arxiv_id":"2406.13631","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-generative-large-language-models-for","title":"Open Generative Large Language Models for Galician","date":"2024-06-19","arxiv_id":"2406.13893","n_code_links":0,"syntology":null},{"paper":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["azzh1/purls"],"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":"generating-educational-materials-with","title":"Generating Educational Materials with Different Levels of Readability using LLMs","date":"2024-06-18","arxiv_id":"2406.12787","n_code_links":0,"syntology":null},{"paper":"/paper/ipeval-a-bilingual-intellectual-property","slug":"ipeval-a-bilingual-intellectual-property","title":"IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models","date":"2024-06-18","arxiv_id":"2406.12386","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-client-centered-assessment-of-llm","slug":"towards-a-client-centered-assessment-of-llm","title":"Towards a Client-Centered Assessment of LLM Therapists by Client Simulation","date":"2024-06-18","arxiv_id":"2406.12266","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wangjs9/clientcast"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"urbanllm-autonomous-urban-activity-planning","title":"UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models","date":"2024-06-18","arxiv_id":"2406.12360","n_code_links":0,"syntology":null},{"paper":null,"slug":"vernacular-i-barely-know-her-challenges-with","title":"Vernacular? I Barely Know Her: Challenges with Style Control and Stereotyping","date":"2024-06-18","arxiv_id":"2406.12679","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-makes-two-models-think-alike","title":"What Makes Two Language Models Think Alike?","date":"2024-06-18","arxiv_id":"2406.12620","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-gotta-be-a-doctor-lin-an-investigation-of","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","date":"2024-06-18","arxiv_id":"2406.12232","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-boundaries-investigating-the-effects","title":"Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance","date":"2024-06-17","arxiv_id":"2406.11139","n_code_links":0,"syntology":null},{"paper":"/paper/building-another-spanish-dictionary-this-time","slug":"building-another-spanish-dictionary-this-time","title":"Building another Spanish dictionary, this time with GPT-4","date":"2024-06-17","arxiv_id":"2406.11218","n_code_links":1,"syntology":null},{"paper":null,"slug":"cultural-conditioning-or-placebo-on-the","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","date":"2024-06-17","arxiv_id":"2406.11661","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-biomedical-knowledge-retrieval","title":"SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation","date":"2024-06-17","arxiv_id":"2406.11258","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-text-classification-through-llm","slug":"enhancing-text-classification-through-llm","title":"Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation","date":"2024-06-17","arxiv_id":"2406.12114","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-the-increase-in-emissions-caused","title":"Estimating the Increase in Emissions caused by AI-augmented Search","date":"2024-06-17","arxiv_id":"2407.16894","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-open-language-models-across-task","slug":"evaluating-open-language-models-across-task","title":"Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?","date":"2024-06-17","arxiv_id":"2406.11402","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-safety-utility-trade-offs-in","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","date":"2024-06-17","arxiv_id":"2406.11107","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-powered-elicitation-interview-script","title":"GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training","date":"2024-06-17","arxiv_id":"2406.11439","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-multi-agent-debate-with-sparse","title":"Improving Multi-Agent Debate with Sparse Communication Topology","date":"2024-06-17","arxiv_id":"2406.11776","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-annotator-bias-in-large","slug":"investigating-annotator-bias-in-large","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","date":"2024-06-17","arxiv_id":"2406.11109","n_code_links":3,"syntology":null},{"paper":null,"slug":"jobfair-a-framework-for-benchmarking-gender","title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","date":"2024-06-17","arxiv_id":"2406.15484","n_code_links":0,"syntology":null},{"paper":null,"slug":"promises-outlooks-and-challenges-of-diffusion","title":"Promises, Outlooks and Challenges of Diffusion Language Modeling","date":"2024-06-17","arxiv_id":"2406.11473","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-the-codebook-size-of-vqgan-to-100000","slug":"scaling-the-codebook-size-of-vqgan-to-100000","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","date":"2024-06-17","arxiv_id":"2406.11837","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zh460045050/vqgan-lc"],"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","unlocated"]}}},{"paper":null,"slug":"self-and-cross-model-distillation-for-llms","title":"Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment","date":"2024-06-17","arxiv_id":"2406.11285","n_code_links":0,"syntology":null},{"paper":"/paper/welldunn-on-the-robustness-and-explainability","slug":"welldunn-on-the-robustness-and-explainability","title":"WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions","date":"2024-06-17","arxiv_id":"2406.12058","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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vedantpalit/WellDunn"],"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":"enhancing-supermarket-robot-interaction-a","title":"Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents","date":"2024-06-16","arxiv_id":"2406.11047","n_code_links":0,"syntology":null},{"paper":null,"slug":"exposing-the-achilles-heel-evaluating-llms","title":"Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning","date":"2024-06-16","arxiv_id":"2406.10834","n_code_links":0,"syntology":null},{"paper":"/paper/generating-tables-from-the-parametric","slug":"generating-tables-from-the-parametric","title":"Generating Tables from the Parametric Knowledge of Language Models","date":"2024-06-16","arxiv_id":"2406.10922","n_code_links":1,"syntology":null},{"paper":null,"slug":"grading-massive-open-online-courses-using","title":"Grading Massive Open Online Courses Using Large Language Models","date":"2024-06-16","arxiv_id":"2406.11102","n_code_links":0,"syntology":null},{"paper":"/paper/kgpa-robustness-evaluation-for-large-language","slug":"kgpa-robustness-evaluation-for-large-language","title":"KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs","date":"2024-06-16","arxiv_id":"2406.10802","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-automatic-milestone","title":"Large Language Models for Automatic Milestone Detection in Group Discussions","date":"2024-06-16","arxiv_id":"2406.10842","n_code_links":0,"syntology":null},{"paper":"/paper/sharelora-parameter-efficient-and-robust","slug":"sharelora-parameter-efficient-and-robust","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.10785","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Rain9876/ShareLoRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vid-gpt-introducing-gpt-style-autoregressive","slug":"vid-gpt-introducing-gpt-style-autoregressive","title":"ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models","date":"2024-06-16","arxiv_id":"2406.10981","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-of-foundation-models","title":"A Comprehensive Survey of Foundation Models in Medicine","date":"2024-06-15","arxiv_id":"2406.10729","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-raw-videos-understanding-edited-videos","slug":"beyond-raw-videos-understanding-edited-videos","title":"Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model","date":"2024-06-15","arxiv_id":"2406.10484","n_code_links":1,"syntology":null},{"paper":"/paper/mint-a-multi-modal-image-and-narrative-text","slug":"mint-a-multi-modal-image-and-narrative-text","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","date":"2024-06-15","arxiv_id":"2406.10591","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-correlation-between-human-and","title":"Exploring the Correlation between Human and Machine Evaluation of Simultaneous Speech Translation","date":"2024-06-14","arxiv_id":"2406.10091","n_code_links":0,"syntology":null},{"paper":"/paper/towards-efficient-pareto-set-approximation","slug":"towards-efficient-pareto-set-approximation","title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","date":"2024-06-14","arxiv_id":"2406.09770","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-more-practical-approach-to-machine","title":"A More Practical Approach to Machine Unlearning","date":"2024-06-13","arxiv_id":"2406.09391","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-bias-in-chatgpt-language-models","title":"Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination","date":"2024-06-13","arxiv_id":"2406.08818","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-large-model-training-through","title":"Optimizing Large Model Training through Overlapped Activation Recomputation","date":"2024-06-13","arxiv_id":"2406.08756","n_code_links":0,"syntology":null},{"paper":null,"slug":"talking-heads-understanding-inter-layer","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","date":"2024-06-13","arxiv_id":"2406.09519","n_code_links":0,"syntology":null},{"paper":null,"slug":"faithfill-faithful-inpainting-for-object","title":"FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image","date":"2024-06-12","arxiv_id":"2406.07865","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuned-small-llms-still-significantly","slug":"fine-tuned-small-llms-still-significantly","title":"Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification","date":"2024-06-12","arxiv_id":"2406.08660","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"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":["mnbucher/text-cls-llms"],"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":"how-well-it-works-benchmarking-performance-of","title":"How well it works: Benchmarking performance of GPT models on medical natural language processing tasks","date":"2024-06-12","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/indirectrequests-making-task-oriented","slug":"indirectrequests-making-task-oriented","title":"Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests","date":"2024-06-12","arxiv_id":"2406.07794","n_code_links":0,"syntology":null},{"paper":"/paper/tailoring-generative-ai-chatbots-for","slug":"tailoring-generative-ai-chatbots-for","title":"Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm","date":"2024-06-12","arxiv_id":"2406.08411","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-words-on-large-language-models","title":"Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis","date":"2024-06-11","arxiv_id":"2406.10273","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-sexism-classification-fine-tuned","title":"Bilingual Sexism Classification: Fine-Tuned XLM-RoBERTa and GPT-3.5 Few-Shot Learning","date":"2024-06-11","arxiv_id":"2406.07287","n_code_links":0,"syntology":null},{"paper":null,"slug":"flextron-many-in-one-flexible-large-language","title":"Flextron: Many-in-One Flexible Large Language Model","date":"2024-06-11","arxiv_id":"2406.10260","n_code_links":0,"syntology":null},{"paper":"/paper/multi-objective-reinforcement-learning-from","slug":"multi-objective-reinforcement-learning-from","title":"Multi-objective Reinforcement learning from AI Feedback","date":"2024-06-11","arxiv_id":"2406.07295","n_code_links":1,"syntology":null},{"paper":"/paper/unused-information-in-token-probability","slug":"unused-information-in-token-probability","title":"Unused information in token probability distribution of generative LLM: improving LLM reading comprehension through calculation of expected values","date":"2024-06-11","arxiv_id":"2406.10267","n_code_links":1,"syntology":null},{"paper":"/paper/agb-de-a-corpus-for-the-automated-legal","slug":"agb-de-a-corpus-for-the-automated-legal","title":"AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts","date":"2024-06-10","arxiv_id":"2406.06809","n_code_links":1,"syntology":null},{"paper":"/paper/compute-better-spent-replacing-dense-layers","slug":"compute-better-spent-replacing-dense-layers","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","date":"2024-06-10","arxiv_id":"2406.06248","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["shikaiqiu/compute-better-spent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/in-context-learning-and-fine-tuning-gpt-for","slug":"in-context-learning-and-fine-tuning-gpt-for","title":"In-Context Learning and Fine-Tuning GPT for Argument Mining","date":"2024-06-10","arxiv_id":"2406.06699","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-dcache-improving-tool-augmented-llms-with","title":"LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching","date":"2024-06-10","arxiv_id":"2406.06799","n_code_links":0,"syntology":null},{"paper":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","n_code_links":0,"syntology":null},{"paper":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","n_code_links":2,"syntology":{"ran":12,"of":12,"n_ran_checked":11,"n_instrument":1,"unverified":0,"pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hidden-holes-topological-aspects-of-language","title":"Hidden Holes: topological aspects of language models","date":"2024-06-09","arxiv_id":"2406.05798","n_code_links":0,"syntology":null},{"paper":null,"slug":"medreqal-examining-medical-knowledge-recall","title":"MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering","date":"2024-06-09","arxiv_id":"2406.05845","n_code_links":0,"syntology":null},{"paper":null,"slug":"text2vp-generative-ai-for-visual-programming","title":"Text2VP: Generative AI for Visual Programming and Parametric Modeling","date":"2024-06-09","arxiv_id":"2407.07732","n_code_links":0,"syntology":null},{"paper":null,"slug":"critical-phase-transition-in-a-large-language","title":"Critical Phase Transition in Large Language Models","date":"2024-06-08","arxiv_id":"2406.05335","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-recognize-me-when-i-is-not-me","title":"Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts","date":"2024-06-08","arxiv_id":"2406.05569","n_code_links":0,"syntology":null},{"paper":null,"slug":"matablegpt-gpt-based-table-data-extractor","title":"MaTableGPT: GPT-based Table Data Extractor from Materials Science Literature","date":"2024-06-08","arxiv_id":"2406.05431","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfdefend-llms-can-defend-themselves-against","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","date":"2024-06-08","arxiv_id":"2406.05498","n_code_links":0,"syntology":null},{"paper":"/paper/bamo-at-semeval-2024-task-9-brainteaser-a","slug":"bamo-at-semeval-2024-task-9-brainteaser-a","title":"BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense","date":"2024-06-07","arxiv_id":"2406.04947","n_code_links":1,"syntology":null},{"paper":"/paper/berts-are-generative-in-context-learners","slug":"berts-are-generative-in-context-learners","title":"BERTs are Generative In-Context Learners","date":"2024-06-07","arxiv_id":"2406.04823","n_code_links":1,"syntology":{"ran":13,"of":26,"n_ran_checked":12,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["ltgoslo/bert-in-context"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Joshuaclymer/GameBench"],"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":"large-generative-graph-models","title":"Large Generative Graph Models","date":"2024-06-07","arxiv_id":"2406.05109","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-cross-lingual-summarization","title":"Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models","date":"2024-06-07","arxiv_id":"2406.04630","n_code_links":0,"syntology":null},{"paper":"/paper/on-subjective-uncertainty-quantification-and","slug":"on-subjective-uncertainty-quantification-and","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","date":"2024-06-07","arxiv_id":"2406.05213","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":0,"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":["meta-inf/suq-nlg"],"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":"vtrans-accelerating-transformer-compression","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","date":"2024-06-07","arxiv_id":"2406.05276","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-medical-large-language-models","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","date":"2024-06-06","arxiv_id":"2406.03712","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-understand-morality","slug":"do-language-models-understand-morality","title":"Do Language Models Understand Morality? Towards a Robust Detection of Moral Content","date":"2024-06-06","arxiv_id":"2406.04143","n_code_links":1,"syntology":null},{"paper":"/paper/horae-a-domain-agnostic-modeling-language-for","slug":"horae-a-domain-agnostic-modeling-language-for","title":"HORAE: A Domain-Agnostic Language for Automated Service Regulation","date":"2024-06-06","arxiv_id":"2406.06600","n_code_links":1,"syntology":null},{"paper":"/paper/llmembed-rethinking-lightweight-llm-s-genuine","slug":"llmembed-rethinking-lightweight-llm-s-genuine","title":"LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification","date":"2024-06-06","arxiv_id":"2406.03725","n_code_links":1,"syntology":null},{"paper":"/paper/simplified-and-generalized-masked-diffusion","slug":"simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","arxiv_id":"2406.04329","n_code_links":1,"syntology":{"ran":6,"of":21,"n_ran_checked":2,"n_instrument":4,"unverified":15,"pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 15 unverified","official":{"repos":["google-deepmind/md4"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":15,"ran_from_kinds":["official"]}}},{"paper":"/paper/tox-bart-leveraging-toxicity-attributes-for","slug":"tox-bart-leveraging-toxicity-attributes-for","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","date":"2024-06-06","arxiv_id":"2406.03953","n_code_links":1,"syntology":null},{"paper":"/paper/your-absorbing-discrete-diffusion-secretly","slug":"your-absorbing-discrete-diffusion-secretly","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","date":"2024-06-06","arxiv_id":"2406.03736","n_code_links":2,"syntology":{"ran":13,"of":13,"n_ran_checked":12,"n_instrument":1,"unverified":0,"pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-gsai/radd"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"1f5f78f67d6247776d747dabb48d8342f341c1ed61ac9ef45234428decdb6d11","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}