{"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/attention-dropout/papers/19","list_of":"/method/attention-dropout","method":"Attention Dropout","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":19,"pages_in_order":109,"rows_per_page":100,"rows":[1801,1900],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"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/attention-dropout","prev":"/method/attention-dropout/papers/18","next":"/method/attention-dropout/papers/20","papers":[{"paper":"/paper/visrag-vision-based-retrieval-augmented","slug":"visrag-vision-based-retrieval-augmented","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","date":"2024-10-14","arxiv_id":"2410.10594","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openbmb/visrag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","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":["brownfortress/llms-trc"],"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":"a-comparative-study-of-pdf-parsing-tools","title":"A Comparative Study of PDF Parsing Tools Across Diverse Document Categories","date":"2024-10-13","arxiv_id":"2410.09871","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-in-context-learning-really-generalize-to","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","date":"2024-10-13","arxiv_id":"2410.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-of-llms-in-making","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","date":"2024-10-13","arxiv_id":"2410.09992","n_code_links":0,"syntology":null},{"paper":null,"slug":"honest-ai-fine-tuning-small-language-models","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","date":"2024-10-13","arxiv_id":"2410.09699","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-implicit-bias-in-large-language","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","date":"2024-10-13","arxiv_id":"2410.12864","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-rank-for-multiple-retrieval","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","date":"2024-10-13","arxiv_id":"2410.09942","n_code_links":0,"syntology":null},{"paper":null,"slug":"m2m-gen-a-multimodal-framework-for-automated","title":"M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models","date":"2024-10-13","arxiv_id":"2410.09928","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-ground-truth-is-not-enough-add","title":"Single Ground Truth Is Not Enough: Add Linguistic Variability to Aspect-based Sentiment Analysis Evaluation","date":"2024-10-13","arxiv_id":"2410.09807","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-speech-recognition-with-bert-and","title":"Automatic Speech Recognition with BERT and CTC Transformers: A Review","date":"2024-10-12","arxiv_id":"2410.09456","n_code_links":0,"syntology":null},{"paper":null,"slug":"llinstruct-an-instruction-tuned-model-for","title":"\\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments","date":"2024-10-12","arxiv_id":"2410.09314","n_code_links":0,"syntology":null},{"paper":"/paper/toward-general-instruction-following","slug":"toward-general-instruction-following","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","date":"2024-10-12","arxiv_id":"2410.09584","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 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) · 2 unverified","official":{"repos":["dongguanting/FollowRAG"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-methodology-for-evaluating-rag-systems-a","slug":"a-methodology-for-evaluating-rag-systems-a","title":"A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation","date":"2024-10-11","arxiv_id":"2410.08801","n_code_links":1,"syntology":null},{"paper":"/paper/attngcg-enhancing-jailbreaking-attacks-on","slug":"attngcg-enhancing-jailbreaking-attacks-on","title":"AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation","date":"2024-10-11","arxiv_id":"2410.09040","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-long-context-performance-in-llms","title":"Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism","date":"2024-10-11","arxiv_id":"2410.12859","n_code_links":0,"syntology":null},{"paper":null,"slug":"extra-global-attention-designation-using","title":"Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures","date":"2024-10-11","arxiv_id":"2410.08971","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-in-house-large-language-models-to","title":"Fine-Tuning In-House Large Language Models to Infer Differential Diagnosis from Radiology Reports","date":"2024-10-11","arxiv_id":"2410.09234","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanity-in-ai-detecting-the-personality-of","title":"Humanity in AI: Detecting the Personality of Large Language Models","date":"2024-10-11","arxiv_id":"2410.08545","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-range-named-entity-recognition-for","title":"Long Range Named Entity Recognition for Marathi Documents","date":"2024-10-11","arxiv_id":"2410.09192","n_code_links":0,"syntology":null},{"paper":null,"slug":"observing-the-southern-us-culture-of-honor","title":"Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysis","date":"2024-10-11","arxiv_id":"2410.13887","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimized-biomedical-question-answering","title":"Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration","date":"2024-10-11","arxiv_id":"2410.12856","n_code_links":0,"syntology":null},{"paper":null,"slug":"oretrieval-augmented-generation-for-10-large","title":"oRetrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical Fitness","date":"2024-10-11","arxiv_id":"2410.08431","n_code_links":0,"syntology":null},{"paper":"/paper/retriever-and-memory-towards-adaptive-note","slug":"retriever-and-memory-towards-adaptive-note","title":"Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation","date":"2024-10-11","arxiv_id":"2410.08821","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thunlp/adaptive-note"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/socialgaze-improving-the-integration-of-human","slug":"socialgaze-improving-the-integration-of-human","title":"SocialGaze: Improving the Integration of Human Social Norms in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08698","n_code_links":1,"syntology":null},{"paper":"/paper/structrag-boosting-knowledge-intensive","slug":"structrag-boosting-knowledge-intensive","title":"StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization","date":"2024-10-11","arxiv_id":"2410.08815","n_code_links":1,"syntology":null},{"paper":"/paper/synth-sonar-sonar-image-synthesis-with","slug":"synth-sonar-sonar-image-synthesis-with","title":"Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting","date":"2024-10-11","arxiv_id":"2410.08612","n_code_links":1,"syntology":null},{"paper":"/paper/adam-exploits-ell-infty-geometry-of-loss","slug":"adam-exploits-ell-infty-geometry-of-loss","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","date":"2024-10-10","arxiv_id":"2410.08198","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["mohamad-amin/adam-coordinate-adaptivity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dice-discrete-inversion-enabling-controllable","title":"DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models","date":"2024-10-10","arxiv_id":"2410.08207","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-you-know-what-you-are-talking-about","title":"Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation","date":"2024-10-10","arxiv_id":"2410.08320","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-language-models-for-ethical","title":"Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses","date":"2024-10-10","arxiv_id":"2410.07826","n_code_links":0,"syntology":null},{"paper":null,"slug":"flier-few-shot-language-image-models-embedded","title":"FLIER: Few-shot Language Image Models Embedded with Latent Representations","date":"2024-10-10","arxiv_id":"2410.07648","n_code_links":0,"syntology":null},{"paper":null,"slug":"news-reporter-a-multi-lingual-llm-framework","title":"News Reporter: A Multi-lingual LLM Framework for Broadcast T.V News","date":"2024-10-10","arxiv_id":"2410.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-free-lunch-retrieval-augmented-generation","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","date":"2024-10-10","arxiv_id":"2410.07589","n_code_links":0,"syntology":null},{"paper":"/paper/privately-learning-from-graphs-with","slug":"privately-learning-from-graphs-with","title":"Privately Learning from Graphs with Applications in Fine-tuning Large Language Models","date":"2024-10-10","arxiv_id":"2410.08299","n_code_links":1,"syntology":null},{"paper":"/paper/robust-ai-generated-text-detection-by","slug":"robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","date":"2024-10-10","arxiv_id":"2410.08113","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["silversolver/robustatd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-rise-of-ai-generated-content-in-wikipedia","slug":"the-rise-of-ai-generated-content-in-wikipedia","title":"The Rise of AI-Generated Content in Wikipedia","date":"2024-10-10","arxiv_id":"2410.08044","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"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":["brooksca3/wiki_collection"],"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":"/paper/turborag-accelerating-retrieval-augmented","slug":"turborag-accelerating-retrieval-augmented","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","date":"2024-10-10","arxiv_id":"2410.07590","n_code_links":1,"syntology":null},{"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":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","n_code_links":1,"syntology":null},{"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":"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":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}],"record_sha256":"3e13b995554251a113f19496fd5047c3b91dc9888b758407fa661033c0ff7dc8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}