{"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/weight-decay/papers/26","list_of":"/method/weight-decay","method":"Weight Decay","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":26,"pages_in_order":108,"rows_per_page":100,"rows":[2501,2600],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/25","next":"/method/weight-decay/papers/27","papers":[{"paper":null,"slug":"intermediate-distillation-data-efficient","title":"Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval","date":"2024-06-18","arxiv_id":"2406.12169","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/planrag-a-plan-then-retrieval-augmented","slug":"planrag-a-plan-then-retrieval-augmented","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","date":"2024-06-18","arxiv_id":"2406.12430","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["myeon9h/planrag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"retrieval-augmented-generation-for-generative","title":"Retrieval-Augmented Generation for Generative Artificial Intelligence in Medicine","date":"2024-06-18","arxiv_id":"2406.12449","n_code_links":0,"syntology":null},{"paper":null,"slug":"richrag-crafting-rich-responses-for-multi","title":"RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation","date":"2024-06-18","arxiv_id":"2406.12566","n_code_links":0,"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":"/paper/unified-active-retrieval-for-retrieval","slug":"unified-active-retrieval-for-retrieval","title":"Unified Active Retrieval for Retrieval Augmented Generation","date":"2024-06-18","arxiv_id":"2406.12534","n_code_links":1,"syntology":null},{"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":"/paper/cram-credibility-aware-attention-modification","slug":"cram-credibility-aware-attention-modification","title":"CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG","date":"2024-06-17","arxiv_id":"2406.11497","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":"/paper/evaluating-the-efficacy-of-open-source-llms","slug":"evaluating-the-efficacy-of-open-source-llms","title":"Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability","date":"2024-06-17","arxiv_id":"2406.11424","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":"fine-tuning-or-fine-failing-debunking","title":"Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models","date":"2024-06-17","arxiv_id":"2406.11201","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":"iterative-utility-judgment-framework-via-llms","title":"Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy","date":"2024-06-17","arxiv_id":"2406.11290","n_code_links":0,"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/r-eval-a-unified-toolkit-for-evaluating","slug":"r-eval-a-unified-toolkit-for-evaluating","title":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models","date":"2024-06-17","arxiv_id":"2406.11681","n_code_links":1,"syntology":null},{"paper":"/paper/satyrn-a-platform-for-analytics-augmented","slug":"satyrn-a-platform-for-analytics-augmented","title":"Satyrn: A Platform for Analytics Augmented Generation","date":"2024-06-17","arxiv_id":"2406.12069","n_code_links":1,"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/textit-refiner-restructure-retrieval-content","slug":"textit-refiner-restructure-retrieval-content","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","date":"2024-06-17","arxiv_id":"2406.11357","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"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) · 1 unverified","official":{"repos":["allen-li1231/refiner-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/trace-the-evidence-constructing-knowledge","slug":"trace-the-evidence-constructing-knowledge","title":"TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation","date":"2024-06-17","arxiv_id":"2406.11460","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jyfang6/trace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/predicting-the-understandability-of","slug":"predicting-the-understandability-of","title":"Predicting the Understandability of Computational Notebooks through Code Metrics Analysis","date":"2024-06-16","arxiv_id":"2406.10989","n_code_links":1,"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":"we-care-multimodal-depression-detection-and","title":"We Care: Multimodal Depression Detection and Knowledge Infused Mental Health Therapeutic Response Generation","date":"2024-06-15","arxiv_id":"2406.10561","n_code_links":0,"syntology":null},{"paper":null,"slug":"bag-of-lies-robustness-in-continuous-pre","title":"Bag of Lies: Robustness in Continuous Pre-training BERT","date":"2024-06-14","arxiv_id":"2406.09967","n_code_links":0,"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/hiro-hierarchical-information-retrieval","slug":"hiro-hierarchical-information-retrieval","title":"HIRO: Hierarchical Information Retrieval Optimization","date":"2024-06-14","arxiv_id":"2406.09979","n_code_links":1,"syntology":null},{"paper":"/paper/the-devil-is-in-the-neurons-interpreting-and","slug":"the-devil-is-in-the-neurons-interpreting-and","title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models","date":"2024-06-14","arxiv_id":"2406.10130","n_code_links":1,"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":"analyzing-gender-polarity-in-short-social","title":"Analyzing Gender Polarity in Short Social Media Texts with BERT: The Role of Emojis and Emoticons","date":"2024-06-13","arxiv_id":"2406.09573","n_code_links":0,"syntology":null},{"paper":"/paper/bpe-knockout-pruning-pre-existing-bpe","slug":"bpe-knockout-pruning-pre-existing-bpe","title":"BPE-knockout: Pruning Pre-existing BPE Tokenisers with Backwards-compatible Morphological Semi-supervision","date":"2024-06-13","arxiv_id":null,"n_code_links":1,"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":"pc-lora-low-rank-adaptation-for-progressive","title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","date":"2024-06-13","arxiv_id":"2406.09117","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":"ad-auctions-for-llms-via-retrieval-augmented","title":"Ad Auctions for LLMs via Retrieval Augmented Generation","date":"2024-06-12","arxiv_id":"2406.09459","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-fact-memorization-and-style","title":"Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods","date":"2024-06-12","arxiv_id":"2406.08582","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/label-aware-hard-negative-sampling-strategies","slug":"label-aware-hard-negative-sampling-strategies","title":"Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech Detection","date":"2024-06-12","arxiv_id":"2406.07886","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-web","title":"Leveraging Large Language Models for Web Scraping","date":"2024-06-12","arxiv_id":"2406.08246","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-representation-loss-between-timed","title":"Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation","date":"2024-06-12","arxiv_id":"2406.08328","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":"covid-19-twitter-sentiment-classification","title":"COVID-19 Twitter Sentiment Classification Using Hybrid Deep Learning Model Based on Grid Search Methodology","date":"2024-06-11","arxiv_id":"2406.10266","n_code_links":0,"syntology":null},{"paper":null,"slug":"dr-rag-applying-dynamic-document-relevance-to","title":"DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering","date":"2024-06-11","arxiv_id":"2406.07348","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/multimodal-belief-prediction","slug":"multimodal-belief-prediction","title":"Multimodal Belief Prediction","date":"2024-06-11","arxiv_id":"2406.07466","n_code_links":1,"syntology":null},{"paper":null,"slug":"question-answering-qa-model-for-a","title":"Question-Answering (QA) Model for a Personalized Learning Assistant for Arabic Language","date":"2024-06-11","arxiv_id":"2406.08519","n_code_links":0,"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":"leveraging-large-language-models-for-12","title":"Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing","date":"2024-06-10","arxiv_id":"2406.06723","n_code_links":0,"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":null,"slug":"the-impact-of-quantization-on-retrieval","title":"The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs","date":"2024-06-10","arxiv_id":"2406.10251","n_code_links":0,"syntology":null},{"paper":"/paper/umbrela-umbrela-is-the-open-source","slug":"umbrela-umbrela-is-the-open-source","title":"UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor","date":"2024-06-10","arxiv_id":"2406.06519","n_code_links":1,"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":"machine-against-the-rag-jamming-retrieval","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","date":"2024-06-09","arxiv_id":"2406.05870","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":"/paper/re-rag-improving-open-domain-qa-performance","slug":"re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","n_code_links":1,"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":"/paper/advancing-semantic-textual-similarity","slug":"advancing-semantic-textual-similarity","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","date":"2024-06-08","arxiv_id":"2406.05326","n_code_links":2,"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":null,"slug":"vp-llm-text-driven-3d-volume-completion-with","title":"VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification","date":"2024-06-08","arxiv_id":"2406.05543","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}],"record_sha256":"a40f62dd420411be32556322386f065c151819040b112b30eb4b89649dca621b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}