{"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/18","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":18,"pages_in_order":108,"rows_per_page":100,"rows":[1701,1800],"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/17","next":"/method/weight-decay/papers/19","papers":[{"paper":"/paper/a-two-model-approach-for-humour-style","slug":"a-two-model-approach-for-humour-style","title":"A Two-Model Approach for Humour Style Recognition","date":"2024-10-09","arxiv_id":"2410.12842","n_code_links":1,"syntology":null},{"paper":null,"slug":"astute-rag-overcoming-imperfect-retrieval","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","date":"2024-10-09","arxiv_id":"2410.07176","n_code_links":0,"syntology":null},{"paper":null,"slug":"autofeedback-an-llm-based-framework-for","title":"AutoFeedback: An LLM-based Framework for Efficient and Accurate API Request Generation","date":"2024-10-09","arxiv_id":"2410.06943","n_code_links":0,"syntology":null},{"paper":null,"slug":"capturing-bias-diversity-in-llms","title":"Capturing Bias Diversity in LLMs","date":"2024-10-09","arxiv_id":"2410.12839","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-model-for-less-resourced-language","title":"Generative Model for Less-Resourced Language with 1 billion parameters","date":"2024-10-09","arxiv_id":"2410.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructional-segment-embedding-improving-llm","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy","date":"2024-10-09","arxiv_id":"2410.09102","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-code-executors-an","title":"Large Language Models as Code Executors: An Exploratory Study","date":"2024-10-09","arxiv_id":"2410.06667","n_code_links":0,"syntology":null},{"paper":null,"slug":"mental-disorders-detection-in-the-era-of","title":"Mental Disorders Detection in the Era of Large Language Models","date":"2024-10-09","arxiv_id":"2410.07129","n_code_links":0,"syntology":null},{"paper":"/paper/mentalarena-self-play-training-of-language","slug":"mentalarena-self-play-training-of-language","title":"MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders","date":"2024-10-09","arxiv_id":"2410.06845","n_code_links":1,"syntology":null},{"paper":null,"slug":"sage-scalable-ground-truth-evaluations-for","title":"SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders","date":"2024-10-09","arxiv_id":"2410.07456","n_code_links":0,"syntology":null},{"paper":"/paper/sparsegrad-a-selective-method-for-efficient","slug":"sparsegrad-a-selective-method-for-efficient","title":"SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers","date":"2024-10-09","arxiv_id":"2410.07383","n_code_links":1,"syntology":null},{"paper":"/paper/the-accuracy-paradox-in-rlhf-when-better","slug":"the-accuracy-paradox-in-rlhf-when-better","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","date":"2024-10-09","arxiv_id":"2410.06554","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["EIT-NLP/AccuracyParadox-RLHF"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-comparative-study-of-hybrid-models-in","title":"A Comparative Study of Hybrid Models in Health Misinformation Text Classification","date":"2024-10-08","arxiv_id":"2410.06311","n_code_links":0,"syntology":null},{"paper":"/paper/a-second-order-like-optimizer-with-adaptive","slug":"a-second-order-like-optimizer-with-adaptive","title":"A second-order-like optimizer with adaptive gradient scaling for deep learning","date":"2024-10-08","arxiv_id":"2410.05871","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-evolve-enhancing-large-language-model-s","title":"Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework","date":"2024-10-08","arxiv_id":"2410.06328","n_code_links":0,"syntology":null},{"paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","slug":"coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.06101","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Harry67Hu/CORY"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-free-energy-in-pretraining-model","title":"Leveraging free energy in pretraining model selection for improved fine-tuning","date":"2024-10-08","arxiv_id":"2410.05612","n_code_links":0,"syntology":null},{"paper":"/paper/lightrag-simple-and-fast-retrieval-augmented","slug":"lightrag-simple-and-fast-retrieval-augmented","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","date":"2024-10-08","arxiv_id":"2410.05779","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkuds/lightrag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"long-context-llms-meet-rag-overcoming","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","date":"2024-10-08","arxiv_id":"2410.05983","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieving-rethinking-and-revising-the-chain","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","date":"2024-10-08","arxiv_id":"2410.05801","n_code_links":0,"syntology":null},{"paper":null,"slug":"anyattack-towards-large-scale-self-supervised","title":"AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models","date":"2024-10-07","arxiv_id":"2410.05346","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-the-interplay-of-parametric-and","slug":"deciphering-the-interplay-of-parametric-and","title":"Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models","date":"2024-10-07","arxiv_id":"2410.05162","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":13,"n_instrument":1,"unverified":3,"pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["m3hrdadfi/rag-memory-interplay"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"etgl-ddpg-a-deep-deterministic-policy","title":"ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control","date":"2024-10-07","arxiv_id":"2410.05225","n_code_links":0,"syntology":null},{"paper":null,"slug":"garlic-llm-guided-dynamic-progress-control","title":"GARLIC: LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph for Long Document QA","date":"2024-10-07","arxiv_id":"2410.04790","n_code_links":0,"syntology":null},{"paper":null,"slug":"lpzero-language-model-zero-cost-proxy-search","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","date":"2024-10-07","arxiv_id":"2410.04808","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-of-thought-improving-temporal","slug":"narrative-of-thought-improving-temporal","title":"Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives","date":"2024-10-07","arxiv_id":"2410.05558","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-instruction-finetuning-neural-machine","title":"On Instruction-Finetuning Neural Machine Translation Models","date":"2024-10-07","arxiv_id":"2410.05553","n_code_links":0,"syntology":null},{"paper":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["famma-bench/bench-script"],"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":"inference-scaling-for-long-context-retrieval","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","date":"2024-10-06","arxiv_id":"2410.04343","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-knowledge-free","title":"Large Language Models for Knowledge-Free Network Management: Feasibility Study and Opportunities","date":"2024-10-06","arxiv_id":"2410.17259","n_code_links":0,"syntology":null},{"paper":null,"slug":"protocollm-automatic-evaluation-framework-of","title":"ProtocoLLM: Automatic Evaluation Framework of LLMs on Domain-Specific Scientific Protocol Formulation Tasks","date":"2024-10-06","arxiv_id":"2410.04601","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-performance-of-human-capable","title":"Assessing the Performance of Human-Capable LLMs -- Are LLMs Coming for Your Job?","date":"2024-10-05","arxiv_id":"2410.16285","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transfer-learning-based-peer-review","title":"Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles","date":"2024-10-05","arxiv_id":"2410.04202","n_code_links":0,"syntology":null},{"paper":"/paper/gamified-crowd-sourcing-of-high-quality-data","slug":"gamified-crowd-sourcing-of-high-quality-data","title":"Gamified crowd-sourcing of high-quality data for visual fine-tuning","date":"2024-10-05","arxiv_id":"2410.04038","n_code_links":0,"syntology":null},{"paper":null,"slug":"metadata-based-data-exploration-with","title":"Metadata-based Data Exploration with Retrieval-Augmented Generation for Large Language Models","date":"2024-10-05","arxiv_id":"2410.04231","n_code_links":0,"syntology":null},{"paper":"/paper/take-it-easy-label-adaptive-self","slug":"take-it-easy-label-adaptive-self","title":"Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation","date":"2024-10-05","arxiv_id":"2410.04002","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":["jingyng/label-adaptive-self-rationalization"],"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":"auto-gda-automatic-domain-adaptation-for","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation","date":"2024-10-04","arxiv_id":"2410.03461","n_code_links":0,"syntology":null},{"paper":null,"slug":"crafting-narrative-closures-zero-shot","title":"Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation","date":"2024-10-04","arxiv_id":"2410.10848","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-transfer-for-automatic-question","title":"Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages","date":"2024-10-04","arxiv_id":"2410.03197","n_code_links":0,"syntology":null},{"paper":"/paper/how-language-models-prioritize-contextual","slug":"how-language-models-prioritize-contextual","title":"How Language Models Prioritize Contextual Grammatical Cues?","date":"2024-10-04","arxiv_id":"2410.03447","n_code_links":1,"syntology":null},{"paper":"/paper/how-much-can-we-forget-about-data","slug":"how-much-can-we-forget-about-data","title":"How Much Can We Forget about Data Contamination?","date":"2024-10-04","arxiv_id":"2410.03249","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tml-tuebingen/forgetting-contamination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-semantic-structure-through-first","title":"Learning Semantic Structure through First-Order-Logic Translation","date":"2024-10-04","arxiv_id":"2410.03203","n_code_links":0,"syntology":null},{"paper":"/paper/steering-large-language-models-between-code","slug":"steering-large-language-models-between-code","title":"Steering Large Language Models between Code Execution and Textual Reasoning","date":"2024-10-04","arxiv_id":"2410.03524","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-list-grounded-question-answering","title":"Structured List-Grounded Question Answering","date":"2024-10-04","arxiv_id":"2410.03950","n_code_links":0,"syntology":null},{"paper":"/paper/swiftkv-fast-prefill-optimized-inference-with","slug":"swiftkv-fast-prefill-optimized-inference-with","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","date":"2024-10-04","arxiv_id":"2410.03960","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-linguistically-aware-and-language","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","date":"2024-10-04","arxiv_id":"2410.03568","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","n_code_links":0,"syntology":null},{"paper":"/paper/variational-language-concepts-for","slug":"variational-language-concepts-for","title":"Variational Language Concepts for Interpreting Foundation Language Models","date":"2024-10-04","arxiv_id":"2410.03964","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-detection-via-topological","slug":"vulnerability-detection-via-topological","title":"Vulnerability Detection via Topological Analysis of Attention Maps","date":"2024-10-04","arxiv_id":"2410.03470","n_code_links":1,"syntology":null},{"paper":"/paper/ward-provable-rag-dataset-inference-via-llm","slug":"ward-provable-rag-dataset-inference-via-llm","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","date":"2024-10-04","arxiv_id":"2410.03537","n_code_links":0,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"a-comprehensive-survey-of-retrieval-augmented","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","date":"2024-10-03","arxiv_id":"2410.12837","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphaintegrator-transformer-action-search-for","title":"AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs","date":"2024-10-03","arxiv_id":"2410.02666","n_code_links":0,"syntology":null},{"paper":"/paper/codejudge-evaluating-code-generation-with","slug":"codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02184","n_code_links":1,"syntology":{"ran":15,"of":23,"n_ran_checked":14,"n_instrument":1,"unverified":8,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["VichyTong/CodeJudge"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/controlled-generation-of-natural-adversarial","slug":"controlled-generation-of-natural-adversarial","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","date":"2024-10-03","arxiv_id":"2410.02163","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-specific-retrieval-augmented","title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","date":"2024-10-03","arxiv_id":"2410.02721","n_code_links":0,"syntology":null},{"paper":"/paper/helmet-how-to-evaluate-long-context-language","slug":"helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","arxiv_id":"2410.02694","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["princeton-nlp/helmet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-much-can-rag-help-the-reasoning-of-llm","title":"How Much Can RAG Help the Reasoning of LLM?","date":"2024-10-03","arxiv_id":"2410.02338","n_code_links":0,"syntology":null},{"paper":null,"slug":"indicsenteval-how-effectively-do-multilingual","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","date":"2024-10-03","arxiv_id":"2410.02611","n_code_links":0,"syntology":null},{"paper":null,"slug":"intrinsic-evaluation-of-rag-systems-for-deep","title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","date":"2024-10-03","arxiv_id":"2410.02932","n_code_links":0,"syntology":null},{"paper":"/paper/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","n_code_links":2,"syntology":null},{"paper":null,"slug":"llava-critic-learning-to-evaluate-multimodal","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02712","n_code_links":0,"syntology":null},{"paper":null,"slug":"morphological-evaluation-of-subwords","title":"Morphological evaluation of subwords vocabulary used by BETO language model","date":"2024-10-03","arxiv_id":"2410.02283","n_code_links":0,"syntology":null},{"paper":null,"slug":"plots-unlock-time-series-understanding-in","title":"Plots Unlock Time-Series Understanding in Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02637","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-rag-enhancing-rag-with-reward-driven","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","date":"2024-10-03","arxiv_id":"2410.03780","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-better-generalization-weight-decay","title":"Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks","date":"2024-10-03","arxiv_id":"2410.02176","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertaintyrag-span-level-uncertainty","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","date":"2024-10-03","arxiv_id":"2410.02719","n_code_links":0,"syntology":null},{"paper":"/paper/visual-editing-with-llm-based-tool-chaining","slug":"visual-editing-with-llm-based-tool-chaining","title":"Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications","date":"2024-10-03","arxiv_id":"2410.02952","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-deductive-coding-in-discourse","slug":"automatic-deductive-coding-in-discourse","title":"Automatic deductive coding in discourse analysis: an application of large language models in learning analytics","date":"2024-10-02","arxiv_id":"2410.01240","n_code_links":1,"syntology":null},{"paper":"/paper/bordirlines-a-dataset-for-evaluating-cross","slug":"bordirlines-a-dataset-for-evaluating-cross","title":"BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation","date":"2024-10-02","arxiv_id":"2410.01171","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["manestay/bordirlines"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emotion-aware-response-generation-using","title":"Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation","date":"2024-10-02","arxiv_id":"2410.01306","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-fine-tuning-for-text-to-sqls-by","title":"Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement","date":"2024-10-02","arxiv_id":"2410.01869","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-retrieval-in-qa-systems-with","slug":"enhancing-retrieval-in-qa-systems-with","title":"Enhancing Retrieval in QA Systems with Derived Feature Association","date":"2024-10-02","arxiv_id":"2410.03754","n_code_links":1,"syntology":null},{"paper":null,"slug":"financial-sentiment-analysis-on-news-and","title":"Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT","date":"2024-10-02","arxiv_id":"2410.01987","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-adaptation-of-unlimiformer-for-decoder","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","date":"2024-10-02","arxiv_id":"2410.01637","n_code_links":0,"syntology":null},{"paper":"/paper/open-rag-enhanced-retrieval-augmented","slug":"open-rag-enhanced-retrieval-augmented","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","date":"2024-10-02","arxiv_id":"2410.01782","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-generalization-complexity-for","slug":"quantifying-generalization-complexity-for","title":"Quantifying Generalization Complexity for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01769","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhentingqi/scylla"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/seeing-eye-to-ai-human-alignment-via-gaze","slug":"seeing-eye-to-ai-human-alignment-via-gaze","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01532","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["telefonica-scientific-research/gaze_reward"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/alignsum-data-pyramid-hierarchical-fine","slug":"alignsum-data-pyramid-hierarchical-fine","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","date":"2024-10-01","arxiv_id":"2410.00409","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csyanghan/alignsum"],"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":"decoding-hate-exploring-language-models","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","date":"2024-10-01","arxiv_id":"2410.00775","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-enhanced-model-for-eye-leme-an-open","title":"Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model","date":"2024-10-01","arxiv_id":"2410.03740","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-attention-decomposition-applied-to","slug":"sparse-attention-decomposition-applied-to","title":"Sparse Attention Decomposition Applied to Circuit Tracing","date":"2024-10-01","arxiv_id":"2410.00340","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-looming-replication-crisis-in-evaluating","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","date":"2024-09-30","arxiv_id":"2409.20303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-explainable-large-language","title":"A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification","date":"2024-09-30","arxiv_id":"2410.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-llms-for-the-medical-domain-in","title":"Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation","date":"2024-09-30","arxiv_id":"2410.00163","n_code_links":0,"syntology":null},{"paper":null,"slug":"bsharedrag-backbone-shared-retrieval","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","date":"2024-09-30","arxiv_id":"2409.20075","n_code_links":0,"syntology":null},{"paper":null,"slug":"depression-detection-in-social-media-posts-1","title":"Depression detection in social media posts using transformer-based models and auxiliary features","date":"2024-09-30","arxiv_id":"2409.20048","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelando-procesos-cognitivos-de-la-lectura","title":"Modelando procesos cognitivos de la lectura natural con GPT-2","date":"2024-09-30","arxiv_id":"2409.20174","n_code_links":0,"syntology":null},{"paper":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","n_code_links":1,"syntology":null},{"paper":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pear-position-embedding-agnostic-attention-re","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","date":"2024-09-29","arxiv_id":"2409.19745","n_code_links":0,"syntology":null},{"paper":"/paper/analog-in-memory-computing-attention","slug":"analog-in-memory-computing-attention","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","date":"2024-09-28","arxiv_id":"2409.19315","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-federated-intrusion-detection-in-5g","slug":"efficient-federated-intrusion-detection-in-5g","title":"Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model","date":"2024-09-28","arxiv_id":"2409.19390","n_code_links":1,"syntology":null},{"paper":"/paper/insightbuddy-ai-medication-extraction-and","slug":"insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","n_code_links":2,"syntology":null},{"paper":null,"slug":"aipatient-simulating-patients-with-ehrs-and","title":"AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow","date":"2024-09-27","arxiv_id":"2409.18924","n_code_links":0,"syntology":null}],"record_sha256":"9997307f96d8ce54daa19658e523687fa274dc7e7bab700276d741e34d2c0b17","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}