{"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/wordpiece/papers/12","list_of":"/method/wordpiece","method":"WordPiece","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":12,"pages_in_order":71,"rows_per_page":100,"rows":[1101,1200],"of":7063,"counts":{"archive_papers_tagged":7063,"with_a_code_link":2910,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7063,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":529,"every_run_a_failure_of_syntologys_instrument":121,"listed_with_a_run_with_no_instrument_failure":529,"listed_every_run_a_failure_of_syntologys_instrument":121,"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/wordpiece","prev":"/method/wordpiece/papers/11","next":"/method/wordpiece/papers/13","papers":[{"paper":null,"slug":"automated-genre-aware-article-scoring-and","title":"Automated Genre-Aware Article Scoring and Feedback Using Large Language Models","date":"2024-10-18","arxiv_id":"2410.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"backdoored-retrievers-for-prompt-injection","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","date":"2024-10-18","arxiv_id":"2410.14479","n_code_links":0,"syntology":null},{"paper":null,"slug":"effects-of-soft-domain-transfer-and-named","title":"Effects of Soft-Domain Transfer and Named Entity Information on Deception Detection","date":"2024-10-18","arxiv_id":"2410.14814","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-contrastive-learning-via-cluster","title":"Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification","date":"2024-10-18","arxiv_id":"2410.18130","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-regularization-of-sharpness-aware","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","date":"2024-10-18","arxiv_id":"2410.14802","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation","title":"Optimizing Retrieval-Augmented Generation with Elasticsearch for Enhanced Question-Answering Systems","date":"2024-10-18","arxiv_id":"2410.14167","n_code_links":0,"syntology":null},{"paper":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","n_code_links":1,"syntology":null},{"paper":"/paper/real-time-fake-news-from-adversarial-feedback","slug":"real-time-fake-news-from-adversarial-feedback","title":"Real-time Fake News from Adversarial Feedback","date":"2024-10-18","arxiv_id":"2410.14651","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-based-on-roberta-for","title":"Sentiment Analysis Based on RoBERTa for Amazon Review: An Empirical Study on Decision Making","date":"2024-10-18","arxiv_id":"2411.00796","n_code_links":0,"syntology":null},{"paper":"/paper/st-moe-bert-a-spatial-temporal-mixture-of","slug":"st-moe-bert-a-spatial-temporal-mixture-of","title":"ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction","date":"2024-10-18","arxiv_id":"2410.14099","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["he-h/HuMob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-systematic-investigation-of-knowledge","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","date":"2024-10-17","arxiv_id":"2410.13258","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-text-generation-in-joint-nlg-nlu","title":"Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques","date":"2024-10-17","arxiv_id":"2410.13498","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-self-generated-documents-for","title":"Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models","date":"2024-10-17","arxiv_id":"2410.13192","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-temporal-representations-for","title":"Integrating Temporal Representations for Dynamic Memory Retrieval and Management in Large Language Models","date":"2024-10-17","arxiv_id":"2410.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistically-grounded-analysis-of-language","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","date":"2024-10-17","arxiv_id":"2410.13396","n_code_links":0,"syntology":null},{"paper":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","n_code_links":1,"syntology":null},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openmatch/rag-ddr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"soullmate-an-application-enhancing-diverse","title":"SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques","date":"2024-10-17","arxiv_id":"2410.16322","n_code_links":0,"syntology":null},{"paper":"/paper/at-rag-an-adaptive-rag-model-enhancing-query","slug":"at-rag-an-adaptive-rag-model-enhancing-query","title":"AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning","date":"2024-10-16","arxiv_id":"2410.12886","n_code_links":1,"syntology":null},{"paper":"/paper/cofe-rag-a-comprehensive-full-chain","slug":"cofe-rag-a-comprehensive-full-chain","title":"CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity","date":"2024-10-16","arxiv_id":"2410.12248","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-attribution-bias-in-retrieval","title":"Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models","date":"2024-10-16","arxiv_id":"2410.12380","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-hate","title":"Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish","date":"2024-10-16","arxiv_id":"2410.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-semantic-chunking-worth-the-computational","title":"Is Semantic Chunking Worth the Computational Cost?","date":"2024-10-16","arxiv_id":"2410.13070","n_code_links":0,"syntology":null},{"paper":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","slug":"mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","arxiv_id":"2410.13085","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["richard-peng-xia/mmed-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/unitary-multi-margin-bert-for-robust-natural","slug":"unitary-multi-margin-bert-for-robust-natural","title":"Unitary Multi-Margin BERT for Robust Natural Language Processing","date":"2024-10-16","arxiv_id":"2410.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"athena-retrieval-augmented-legal-judgment","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","date":"2024-10-15","arxiv_id":"2410.11195","n_code_links":0,"syntology":null},{"paper":"/paper/dynamicer-resolving-emerging-mentions-to","slug":"dynamicer-resolving-emerging-mentions-to","title":"DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG","date":"2024-10-15","arxiv_id":"2410.11494","n_code_links":1,"syntology":null},{"paper":null,"slug":"holistic-reasoning-with-long-context-lms-a","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","date":"2024-10-15","arxiv_id":"2410.11996","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-capacity-of-citation-generation-by","title":"On the Capacity of Citation Generation by Large Language Models","date":"2024-10-15","arxiv_id":"2410.11217","n_code_links":0,"syntology":null},{"paper":"/paper/pixology-probing-the-linguistic-and-visual","slug":"pixology-probing-the-linguistic-and-visual","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","date":"2024-10-15","arxiv_id":"2410.12011","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kushaltatariya/Pixology"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"redeep-detecting-hallucination-in-retrieval","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","date":"2024-10-15","arxiv_id":"2410.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","n_code_links":0,"syntology":null},{"paper":"/paper/rulerag-rule-guided-retrieval-augmented","slug":"rulerag-rule-guided-retrieval-augmented","title":"RuleRAG: Rule-guided retrieval-augmented generation with language models for question answering","date":"2024-10-15","arxiv_id":"2410.22353","n_code_links":1,"syntology":null},{"paper":null,"slug":"seer-self-aligned-evidence-extraction-for","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11315","n_code_links":0,"syntology":null},{"paper":"/paper/self-adaptive-multimodal-retrieval-augmented","slug":"self-adaptive-multimodal-retrieval-augmented","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11321","n_code_links":1,"syntology":null},{"paper":null,"slug":"sorted-weight-sectioning-for-energy-efficient","title":"Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars","date":"2024-10-15","arxiv_id":"2410.11298","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-interlocutors-experiments-with","title":"Synthetic Interlocutors. Experiments with Generative AI to Prolong Ethnographic Encounters","date":"2024-10-15","arxiv_id":"2410.11395","n_code_links":0,"syntology":null},{"paper":null,"slug":"telco-dpr-a-hybrid-dataset-for-evaluating","title":"Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications","date":"2024-10-15","arxiv_id":"2410.19790","n_code_links":0,"syntology":null},{"paper":"/paper/an-annotated-dataset-of-errors-in-premodern","slug":"an-annotated-dataset-of-errors-in-premodern","title":"An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them","date":"2024-10-14","arxiv_id":"2410.11071","n_code_links":1,"syntology":null},{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-rag-question-identification-and-answer","title":"Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations","date":"2024-10-14","arxiv_id":"2410.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"dissecting-embedding-method-learning-higher","title":"Dissecting embedding method: learning higher-order structures from data","date":"2024-10-14","arxiv_id":"2410.10917","n_code_links":0,"syntology":null},{"paper":"/paper/easyrag-efficient-retrieval-augmented","slug":"easyrag-efficient-retrieval-augmented","title":"EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations","date":"2024-10-14","arxiv_id":"2410.10315","n_code_links":1,"syntology":null},{"paper":null,"slug":"funnelrag-a-coarse-to-fine-progressive","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","date":"2024-10-14","arxiv_id":"2410.10293","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-of-llm-in-economics-an","title":"Gender Bias of LLM in Economics: An Existentialism Perspective","date":"2024-10-14","arxiv_id":"2410.19775","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-records-boosting-retrieval-augmented","slug":"graph-of-records-boosting-retrieval-augmented","title":"Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs","date":"2024-10-14","arxiv_id":"2410.11001","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-legal-judgement-prediction-in-a","slug":"rethinking-legal-judgement-prediction-in-a","title":"Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10542","n_code_links":1,"syntology":null},{"paper":"/paper/rocoft-efficient-finetuning-of-large-language","slug":"rocoft-efficient-finetuning-of-large-language","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","date":"2024-10-14","arxiv_id":"2410.10075","n_code_links":1,"syntology":null},{"paper":null,"slug":"stackfeed-structured-textual-actor-critic","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","date":"2024-10-14","arxiv_id":"2410.10584","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-multi-head-attention-via","slug":"towards-better-multi-head-attention-via","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","date":"2024-10-14","arxiv_id":"2410.10914","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"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) · 3 unverified","official":{"repos":["dashenzi721/csp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":"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":"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":"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":"/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":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":"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":"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/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":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":"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/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":"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":"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/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":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":"/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":"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":"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":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":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":"/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}],"record_sha256":"b56da1440e8d102583c4f74749d1d934d83f04f1599b5e9d3bb62261fd6d095c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}