{"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/6","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":6,"pages_in_order":71,"rows_per_page":100,"rows":[501,600],"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/5","next":"/method/wordpiece/papers/7","papers":[{"paper":"/paper/bridging-legal-knowledge-and-ai-retrieval","slug":"bridging-legal-knowledge-and-ai-retrieval","title":"Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization","date":"2025-02-27","arxiv_id":"2502.20364","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-much-is-enough-the-diminishing-returns-of","title":"How Much is Enough? The Diminishing Returns of Tokenization Training Data","date":"2025-02-27","arxiv_id":"2502.20273","n_code_links":0,"syntology":null},{"paper":"/paper/long-context-inference-with-retrieval","slug":"long-context-inference-with-retrieval","title":"Long-Context Inference with Retrieval-Augmented Speculative Decoding","date":"2025-02-27","arxiv_id":"2502.20330","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-federated-search-for-retrieval","title":"Efficient Federated Search for Retrieval-Augmented Generation","date":"2025-02-26","arxiv_id":"2502.19280","n_code_links":0,"syntology":null},{"paper":null,"slug":"mebench-benchmarking-large-language-models","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","date":"2025-02-26","arxiv_id":"2502.18993","n_code_links":0,"syntology":null},{"paper":"/paper/neobert-a-next-generation-bert","slug":"neobert-a-next-generation-bert","title":"NeoBERT: A Next-Generation BERT","date":"2025-02-26","arxiv_id":"2502.19587","n_code_links":1,"syntology":null},{"paper":null,"slug":"broadening-discovery-through-structural","title":"Broadening Discovery through Structural Models: Multimodal Combination of Local and Structural Properties for Predicting Chemical Features","date":"2025-02-25","arxiv_id":"2502.17986","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-knowledge-boundary-of-vision-large","title":"Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference","date":"2025-02-25","arxiv_id":"2502.18023","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-text-classification-with-a-novel","title":"Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT","date":"2025-02-25","arxiv_id":"2502.18653","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-cheaper-better-multi-objective","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","date":"2025-02-25","arxiv_id":"2502.18635","n_code_links":0,"syntology":null},{"paper":"/paper/levelrag-enhancing-retrieval-augmented","slug":"levelrag-enhancing-retrieval-augmented","title":"LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers","date":"2025-02-25","arxiv_id":"2502.18139","n_code_links":1,"syntology":null},{"paper":"/paper/mm-poisonrag-disrupting-multimodal-rag-with","slug":"mm-poisonrag-disrupting-multimodal-rag-with","title":"MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks","date":"2025-02-25","arxiv_id":"2502.17832","n_code_links":1,"syntology":null},{"paper":null,"slug":"mucos-efficient-drug-target-prediction","title":"MuCoS: Efficient Drug-Target Prediction through Multi-Context-Aware Sampling","date":"2025-02-25","arxiv_id":"2502.17784","n_code_links":0,"syntology":null},{"paper":null,"slug":"say-less-mean-more-leveraging-pragmatics-in","title":"Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation","date":"2025-02-25","arxiv_id":"2502.17839","n_code_links":0,"syntology":null},{"paper":"/paper/vidorag-visual-document-retrieval-augmented","slug":"vidorag-visual-document-retrieval-augmented","title":"ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents","date":"2025-02-25","arxiv_id":"2502.18017","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":0,"n_instrument":1,"unverified":5,"pointer_only":6,"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) · 5 unverified","official":{"repos":["Alibaba-NLP/ViDoRAG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"actionable-help-in-crises-a-novel-dataset-and","title":"\"Actionable Help\" in Crises: A Novel Dataset and Resource-Efficient Models for Identifying Request and Offer Social Media Posts","date":"2025-02-24","arxiv_id":"2502.16839","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-training-for-defense-against","slug":"adversarial-training-for-defense-against","title":"Adversarial Training for Defense Against Label Poisoning Attacks","date":"2025-02-24","arxiv_id":"2502.17121","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":["melisilaydabal/floral"],"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":null,"slug":"applying-llms-to-active-learning-towards-cost","title":"Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data","date":"2025-02-24","arxiv_id":"2502.16892","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-retrieval-augmented-generation-1","slug":"benchmarking-retrieval-augmented-generation-1","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","date":"2025-02-24","arxiv_id":"2502.17297","n_code_links":2,"syntology":null},{"paper":null,"slug":"evaluating-the-effect-of-retrieval","title":"Evaluating the Effect of Retrieval Augmentation on Social Biases","date":"2025-02-24","arxiv_id":"2502.17611","n_code_links":0,"syntology":null},{"paper":"/paper/lettucedetect-a-hallucination-detection","slug":"lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","n_code_links":2,"syntology":null},{"paper":"/paper/memerag-a-multilingual-end-to-end-meta","slug":"memerag-a-multilingual-end-to-end-meta","title":"MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation","date":"2025-02-24","arxiv_id":"2502.17163","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-bias-in-rag-controlling-the","slug":"mitigating-bias-in-rag-controlling-the","title":"Mitigating Bias in RAG: Controlling the Embedder","date":"2025-02-24","arxiv_id":"2502.17390","n_code_links":1,"syntology":null},{"paper":null,"slug":"mutual-reinforcement-of-llm-dialogue","title":"Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization","date":"2025-02-24","arxiv_id":"2502.17328","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-typologically-aware-rescoring-to","title":"Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages","date":"2025-02-24","arxiv_id":"2502.17664","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-chain-of-thought-reasoning-for","title":"D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models","date":"2025-02-23","arxiv_id":"2502.16540","n_code_links":0,"syntology":null},{"paper":"/paper/code-summarization-beyond-function-level","slug":"code-summarization-beyond-function-level","title":"Code Summarization Beyond Function Level","date":"2025-02-23","arxiv_id":"2502.16704","n_code_links":1,"syntology":null},{"paper":null,"slug":"layer-wise-evolution-of-representations-in","title":"Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders","date":"2025-02-23","arxiv_id":"2502.16722","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation-of","title":"Optimizing Retrieval-Augmented Generation of Medical Content for Spaced Repetition Learning","date":"2025-02-23","arxiv_id":"2503.01859","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-visual-question-answering-1","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","date":"2025-02-23","arxiv_id":"2502.16641","n_code_links":0,"syntology":null},{"paper":"/paper/visual-rag-benchmarking-text-to-image","slug":"visual-rag-benchmarking-text-to-image","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","date":"2025-02-23","arxiv_id":"2502.16636","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-end-to-end-homomorphically-encrypted","title":"An End-to-End Homomorphically Encrypted Neural Network","date":"2025-02-22","arxiv_id":"2502.16176","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-auto-annotation-for-scientific","title":"Iterative Auto-Annotation for Scientific Named Entity Recognition Using BERT-Based Models","date":"2025-02-22","arxiv_id":"2502.16312","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-enhanced-collaborative-llm-agents-for","title":"RAG-Enhanced Collaborative LLM Agents for Drug Discovery","date":"2025-02-22","arxiv_id":"2502.17506","n_code_links":0,"syntology":null},{"paper":null,"slug":"worse-than-zero-shot-a-fact-checking-dataset","title":"Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals","date":"2025-02-22","arxiv_id":"2502.16101","n_code_links":0,"syntology":null},{"paper":"/paper/a-close-look-at-decomposition-based-xai","slug":"a-close-look-at-decomposition-based-xai","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","date":"2025-02-21","arxiv_id":"2502.15886","n_code_links":2,"syntology":null},{"paper":null,"slug":"chain-of-rank-enhancing-large-language-models","title":"Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device","date":"2025-02-21","arxiv_id":"2502.15134","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-format-retrieval-augmented-generation","title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","date":"2025-02-21","arxiv_id":"2502.15604","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-domain-specific-retrieval-augmented","slug":"enhancing-domain-specific-retrieval-augmented","title":"Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models","date":"2025-02-21","arxiv_id":"2502.15854","n_code_links":1,"syntology":null},{"paper":null,"slug":"extraction-multi-etiquettes-de-relations-en","title":"Extraction multi-étiquettes de relations en utilisant des couches de Transformer","date":"2025-02-21","arxiv_id":"2502.15619","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-speech-recognition","title":"Retrieval-Augmented Speech Recognition Approach for Domain Challenges","date":"2025-02-21","arxiv_id":"2502.15264","n_code_links":0,"syntology":null},{"paper":"/paper/robust-bias-detection-in-mlms-and-its","slug":"robust-bias-detection-in-mlms-and-its","title":"Robust Bias Detection in MLMs and its Application to Human Trait Ratings","date":"2025-02-21","arxiv_id":"2502.15600","n_code_links":1,"syntology":null},{"paper":null,"slug":"tokenization-is-sensitive-to-language","title":"Tokenization is Sensitive to Language Variation","date":"2025-02-21","arxiv_id":"2502.15343","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-socratic-rag-approach-to-connect-natural","title":"A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems","date":"2025-02-20","arxiv_id":"2502.15005","n_code_links":0,"syntology":null},{"paper":null,"slug":"find-fine-grained-information-density-guided","title":"FIND: Fine-grained Information Density Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis","date":"2025-02-20","arxiv_id":"2502.14614","n_code_links":0,"syntology":null},{"paper":"/paper/from-rag-to-memory-non-parametric-continual","slug":"from-rag-to-memory-non-parametric-continual","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14802","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["osu-nlp-group/hipporag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"is-relevance-propagated-from-retriever-to","title":"Is Relevance Propagated from Retriever to Generator in RAG?","date":"2025-02-20","arxiv_id":"2502.15025","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-influence-of-context-size-and-model","slug":"on-the-influence-of-context-size-and-model","title":"On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems","date":"2025-02-20","arxiv_id":"2502.14759","n_code_links":1,"syntology":null},{"paper":null,"slug":"paperhelper-knowledge-based-llm-qa-paper","title":"PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant","date":"2025-02-20","arxiv_id":"2502.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"quad-llm-mltc-large-language-models-ensemble","title":"QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification","date":"2025-02-20","arxiv_id":"2502.14189","n_code_links":0,"syntology":null},{"paper":null,"slug":"wavrag-audio-integrated-retrieval-augmented","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","date":"2025-02-20","arxiv_id":"2502.14727","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-in-context-graph","title":"Are Large Language Models In-Context Graph Learners?","date":"2025-02-19","arxiv_id":"2502.13562","n_code_links":0,"syntology":null},{"paper":null,"slug":"dh-rag-a-dynamic-historical-context-powered","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","date":"2025-02-19","arxiv_id":"2502.13847","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-social-connections-from-finnish","title":"Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs","date":"2025-02-19","arxiv_id":"2502.13566","n_code_links":0,"syntology":null},{"paper":null,"slug":"hawkbench-investigating-resilience-of-rag","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","date":"2025-02-19","arxiv_id":"2502.13465","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-place-updates-of-a-graph-index-for","title":"In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search","date":"2025-02-19","arxiv_id":"2502.13826","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-gym-optimizing-reasoning-and-search","title":"RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision","date":"2025-02-19","arxiv_id":"2502.13957","n_code_links":0,"syntology":null},{"paper":null,"slug":"rgar-recurrence-generation-augmented","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","date":"2025-02-19","arxiv_id":"2502.13361","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-semantic-embeddings-of-chemical","title":"Universal Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery","date":"2025-02-19","arxiv_id":"2502.14912","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-are-models-thinking-about-understanding","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","date":"2025-02-19","arxiv_id":"2502.13490","n_code_links":0,"syntology":null},{"paper":null,"slug":"hoprag-multi-hop-reasoning-for-logic-aware","title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","date":"2025-02-18","arxiv_id":"2502.12442","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-clinical-question-answering-with","title":"Improving Clinical Question Answering with Multi-Task Learning: A Joint Approach for Answer Extraction and Medical Categorization","date":"2025-02-18","arxiv_id":"2502.13108","n_code_links":0,"syntology":null},{"paper":null,"slug":"oreo-a-plug-in-context-reconstructor-to","title":"Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation","date":"2025-02-18","arxiv_id":"2502.13019","n_code_links":0,"syntology":null},{"paper":"/paper/pathrag-pruning-graph-based-retrieval","slug":"pathrag-pruning-graph-based-retrieval","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","date":"2025-02-18","arxiv_id":"2502.14902","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["bupt-gamma/pathrag"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/adasplash-adaptive-sparse-flash-attention","slug":"adasplash-adaptive-sparse-flash-attention","title":"AdaSplash: Adaptive Sparse Flash Attention","date":"2025-02-17","arxiv_id":"2502.12082","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["deep-spin/adasplash"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-llms-simulate-social-media-engagement-a","title":"Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation","date":"2025-02-17","arxiv_id":"2502.12073","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-rag-really-perform-bad-for-long-context","title":"Does RAG Really Perform Bad For Long-Context Processing?","date":"2025-02-17","arxiv_id":"2502.11444","n_code_links":0,"syntology":null},{"paper":"/paper/fast-or-better-balancing-accuracy-and-cost-in","slug":"fast-or-better-balancing-accuracy-and-cost-in","title":"Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control","date":"2025-02-17","arxiv_id":"2502.12145","n_code_links":1,"syntology":null},{"paper":null,"slug":"finefilter-a-fine-grained-noise-filtering","title":"FineFilter: A Fine-grained Noise Filtering Mechanism for Retrieval-Augmented Large Language Models","date":"2025-02-17","arxiv_id":"2502.11811","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-vs-graphrag-a-systematic-evaluation-and","title":"RAG vs. GraphRAG: A Systematic Evaluation and Key Insights","date":"2025-02-17","arxiv_id":"2502.11371","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-mm-rag-a-real-world-multi-modal","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","date":"2025-02-17","arxiv_id":"2502.12342","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-financial-sentiment-analysis-a","slug":"revisiting-financial-sentiment-analysis-a","title":"Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting","date":"2025-02-17","arxiv_id":"2502.14897","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-robust-rag-do-we-still-need","title":"Revisiting Robust RAG: Do We Still Need Complex Robust Training in the Era of Powerful LLMs?","date":"2025-02-17","arxiv_id":"2502.11400","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geometry-of-bert","title":"The geometry of BERT","date":"2025-02-17","arxiv_id":"2502.12033","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-enabling-natural-language","title":"Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation","date":"2025-02-16","arxiv_id":"2502.11201","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-language-models-for-enhanced","title":"Integrating Language Models for Enhanced Network State Monitoring in DRL-Based SFC Provisioning","date":"2025-02-16","arxiv_id":"2502.11298","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-language-preference-of","title":"Investigating Language Preference of Multilingual RAG Systems","date":"2025-02-16","arxiv_id":"2502.11175","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-conditional-mutual-information-to","title":"Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification","date":"2025-02-16","arxiv_id":"2502.11258","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitend-a-multilingual-benchmark-for","title":"MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translation","date":"2025-02-16","arxiv_id":"2502.11022","n_code_links":0,"syntology":null},{"paper":null,"slug":"quote-question-oriented-text-embeddings","title":"QuOTE: Question-Oriented Text Embeddings","date":"2025-02-16","arxiv_id":"2502.10976","n_code_links":0,"syntology":null},{"paper":null,"slug":"roserag-robust-retrieval-augmented-generation","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","date":"2025-02-16","arxiv_id":"2502.10993","n_code_links":0,"syntology":null},{"paper":null,"slug":"speecht-rag-reliable-depression-detection-in","title":"SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information","date":"2025-02-16","arxiv_id":"2502.10950","n_code_links":0,"syntology":null},{"paper":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","n_code_links":0,"syntology":null},{"paper":"/paper/citecheck-towards-accurate-citation","slug":"citecheck-towards-accurate-citation","title":"CiteCheck: Towards Accurate Citation Faithfulness Detection","date":"2025-02-15","arxiv_id":"2502.10881","n_code_links":1,"syntology":null},{"paper":null,"slug":"dataset-protection-via-watermarked-canaries","title":"Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs","date":"2025-02-15","arxiv_id":"2502.10673","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolving-hate-speech-online-an-adaptive","title":"Evolving Hate Speech Online: An Adaptive Framework for Detection and Mitigation","date":"2025-02-15","arxiv_id":"2502.10921","n_code_links":0,"syntology":null},{"paper":"/paper/nitibench-a-comprehensive-studies-of-llm","slug":"nitibench-a-comprehensive-studies-of-llm","title":"NitiBench: A Comprehensive Studies of LLM Frameworks Capabilities for Thai Legal Question Answering","date":"2025-02-15","arxiv_id":"2502.10868","n_code_links":1,"syntology":null},{"paper":null,"slug":"archrag-attributed-community-based","title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","date":"2025-02-14","arxiv_id":"2502.09891","n_code_links":0,"syntology":null},{"paper":null,"slug":"embbert-q-breaking-memory-barriers-in","title":"EmbBERT-Q: Breaking Memory Barriers in Embedded NLP","date":"2025-02-14","arxiv_id":"2502.10001","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucinations-and-truth-a-comprehensive","title":"Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA","date":"2025-02-14","arxiv_id":"2502.10497","n_code_links":0,"syntology":null},{"paper":null,"slug":"lara-benchmarking-retrieval-augmented","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs - No Silver Bullet for LC or RAG Routing","date":"2025-02-14","arxiv_id":"2502.09977","n_code_links":0,"syntology":null},{"paper":null,"slug":"post-training-an-llm-for-rag-train-on-self","title":"Post-training an LLM for RAG? Train on Self-Generated Demonstrations","date":"2025-02-14","arxiv_id":"2502.10596","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-rag-with-active-learning-on","title":"Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables","date":"2025-02-13","arxiv_id":"2502.09073","n_code_links":0,"syntology":null},{"paper":null,"slug":"kimas-a-configurable-knowledge-integrated","title":"KIMAs: A Configurable Knowledge Integrated Multi-Agent System","date":"2025-02-13","arxiv_id":"2502.09596","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-cognitive-decline-a-multimodal-ai","title":"Predicting Cognitive Decline: A Multimodal AI Approach to Dementia Screening from Speech","date":"2025-02-13","arxiv_id":"2502.08862","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-pre-trained-and-large-language","title":"Utilizing Pre-trained and Large Language Models for 10-K Items Segmentation","date":"2025-02-13","arxiv_id":"2502.08875","n_code_links":0,"syntology":null},{"paper":"/paper/ask-in-any-modality-a-comprehensive-survey-on","slug":"ask-in-any-modality-a-comprehensive-survey-on","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","date":"2025-02-12","arxiv_id":"2502.08826","n_code_links":1,"syntology":null},{"paper":null,"slug":"paretorag-leveraging-sentence-context","title":"ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation","date":"2025-02-12","arxiv_id":"2502.08178","n_code_links":0,"syntology":null},{"paper":"/paper/systematic-knowledge-injection-into-large","slug":"systematic-knowledge-injection-into-large","title":"Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG","date":"2025-02-12","arxiv_id":"2502.08356","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kushagrabhushan/Systematic-Knowledge-Injection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-advanced-nlp-framework-for-automated","title":"An Advanced NLP Framework for Automated Medical Diagnosis with DeBERTa and Dynamic Contextual Positional Gating","date":"2025-02-11","arxiv_id":"2502.07755","n_code_links":0,"syntology":null}],"record_sha256":"3e9ff59dcb4299d7174b8a64fcff8c9e967c1d6b3c507b1a5f3e8988d621f4e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}