{"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/3","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":3,"pages_in_order":71,"rows_per_page":100,"rows":[201,300],"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/2","next":"/method/wordpiece/papers/4","papers":[{"paper":null,"slug":"osiris-a-lightweight-open-source","title":"Osiris: A Lightweight Open-Source Hallucination Detection System","date":"2025-05-07","arxiv_id":"2505.04844","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-risks-and-regulatory-strategies","title":"Personalized Risks and Regulatory Strategies of Large Language Models in Digital Advertising","date":"2025-05-07","arxiv_id":"2505.04665","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-evaluation-for","title":"Retrieval Augmented Generation Evaluation for Health Documents","date":"2025-05-07","arxiv_id":"2505.04680","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-reasoning-focused-legal-retrieval-benchmark","title":"A Reasoning-Focused Legal Retrieval Benchmark","date":"2025-05-06","arxiv_id":"2505.03970","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-hyper-parameter-optimization","title":"An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation","date":"2025-05-06","arxiv_id":"2505.03452","n_code_links":0,"syntology":null},{"paper":null,"slug":"hesitation-is-defeat-connecting-linguistic","title":"Hesitation is defeat? Connecting Linguistic and Predictive Uncertainty","date":"2025-05-06","arxiv_id":"2505.03910","n_code_links":0,"syntology":null},{"paper":"/paper/indicsquad-a-comprehensive-multilingual","slug":"indicsquad-a-comprehensive-multilingual","title":"IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages","date":"2025-05-06","arxiv_id":"2505.03688","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-for-learning-on-noisy-and-task","title":"Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights","date":"2025-05-06","arxiv_id":"2505.03205","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-email-spam-detection-leveraging","slug":"advancing-email-spam-detection-leveraging","title":"Advancing Email Spam Detection: Leveraging Zero-Shot Learning and Large Language Models","date":"2025-05-05","arxiv_id":"2505.02362","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-proficiency-assessment-in-l2","title":"Automatic Proficiency Assessment in L2 English Learners","date":"2025-05-05","arxiv_id":"2505.02615","n_code_links":0,"syntology":null},{"paper":"/paper/direct-retrieval-augmented-optimization","slug":"direct-retrieval-augmented-optimization","title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","date":"2025-05-05","arxiv_id":"2505.03075","n_code_links":1,"syntology":null},{"paper":"/paper/knowing-you-don-t-know-learning-when-to","slug":"knowing-you-don-t-know-learning-when-to","title":"Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing","date":"2025-05-05","arxiv_id":"2505.02811","n_code_links":1,"syntology":null},{"paper":null,"slug":"less-is-more-efficient-weight-farcasting-with","title":"Less is More: Efficient Weight Farcasting with 1-Layer Neural Network","date":"2025-05-05","arxiv_id":"2505.02714","n_code_links":0,"syntology":null},{"paper":null,"slug":"rapid-yet-accurate-tile-circuit-and-device","title":"Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing","date":"2025-05-05","arxiv_id":"2506.00004","n_code_links":0,"syntology":null},{"paper":null,"slug":"symbioticrag-enhancing-document-intelligence","title":"SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration","date":"2025-05-05","arxiv_id":"2505.02418","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-hope-domain-agnostic-automatic","title":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","date":"2025-05-04","arxiv_id":"2505.02171","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-cooperative-rationalization-the","slug":"adversarial-cooperative-rationalization-the","title":"Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets","date":"2025-05-04","arxiv_id":"2505.02118","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["jugechengzi/rationalization-a2i"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-new-approaches-for-information","title":"Exploring new Approaches for Information Retrieval through Natural Language Processing","date":"2025-05-04","arxiv_id":"2505.02199","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-spatial-retrieval-augmented","title":"Real-time Spatial Retrieval Augmented Generation for Urban Environments","date":"2025-05-04","arxiv_id":"2505.02271","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-in-context-learning-for","title":"Retrieval-augmented in-context learning for multimodal large language models in disease classification","date":"2025-05-04","arxiv_id":"2505.02087","n_code_links":0,"syntology":null},{"paper":null,"slug":"positional-attention-for-efficient-bert-based","title":"Positional Attention for Efficient BERT-Based Named Entity Recognition","date":"2025-05-03","arxiv_id":"2505.01868","n_code_links":0,"syntology":null},{"paper":null,"slug":"chorus-zero-shot-hierarchical-retrieval-and","title":"CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code","date":"2025-05-02","arxiv_id":"2505.01485","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-in-biomedicine","title":"Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications","date":"2025-05-02","arxiv_id":"2505.01146","n_code_links":0,"syntology":null},{"paper":"/paper/cse-sfp-enabling-unsupervised-sentence","slug":"cse-sfp-enabling-unsupervised-sentence","title":"CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass","date":"2025-05-01","arxiv_id":"2505.00389","n_code_links":1,"syntology":null},{"paper":null,"slug":"enronqa-towards-personalized-rag-over-private","title":"EnronQA: Towards Personalized RAG over Private Documents","date":"2025-05-01","arxiv_id":"2505.00263","n_code_links":0,"syntology":null},{"paper":null,"slug":"patchwork-a-unified-framework-for-rag-serving","title":"Patchwork: A Unified Framework for RAG Serving","date":"2025-05-01","arxiv_id":"2505.07833","n_code_links":0,"syntology":null},{"paper":"/paper/llm-empowered-embodied-agent-for-memory","slug":"llm-empowered-embodied-agent-for-memory","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","date":"2025-04-30","arxiv_id":"2504.21716","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["marc1198/chat-hsr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/talk-before-you-retrieve-agent-led","slug":"talk-before-you-retrieve-agent-led","title":"Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA","date":"2025-04-30","arxiv_id":"2504.21252","n_code_links":1,"syntology":null},{"paper":null,"slug":"traceback-of-poisoning-attacks-to-retrieval","title":"Traceback of Poisoning Attacks to Retrieval-Augmented Generation","date":"2025-04-30","arxiv_id":"2504.21668","n_code_links":0,"syntology":null},{"paper":null,"slug":"arcs-agentic-retrieval-augmented-code","title":"ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement","date":"2025-04-29","arxiv_id":"2504.20434","n_code_links":0,"syntology":null},{"paper":"/paper/brightcookies-at-semeval-2025-task-9","slug":"brightcookies-at-semeval-2025-task-9","title":"BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification","date":"2025-04-29","arxiv_id":"2504.20703","n_code_links":1,"syntology":null},{"paper":"/paper/cbm-rag-demonstrating-enhanced","slug":"cbm-rag-demonstrating-enhanced","title":"CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck Models","date":"2025-04-29","arxiv_id":"2504.20898","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-rag-for-legal-norms-a-hierarchical-and","title":"Graph RAG for Legal Norms: A Hierarchical and Temporal Approach","date":"2025-04-29","arxiv_id":"2505.00039","n_code_links":0,"syntology":null},{"paper":"/paper/reasonir-training-retrievers-for-reasoning","slug":"reasonir-training-retrievers-for-reasoning","title":"ReasonIR: Training Retrievers for Reasoning Tasks","date":"2025-04-29","arxiv_id":"2504.20595","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/reasonir"],"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/universalrag-retrieval-augmented-generation","slug":"universalrag-retrieval-augmented-generation","title":"UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities","date":"2025-04-29","arxiv_id":"2504.20734","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-be-trusted-for-evaluating-rag","title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","date":"2025-04-28","arxiv_id":"2504.20119","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbot-arena-meets-nuggets-towards","title":"Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses","date":"2025-04-28","arxiv_id":"2504.20006","n_code_links":0,"syntology":null},{"paper":"/paper/reconstructing-context-evaluating-advanced","slug":"reconstructing-context-evaluating-advanced","title":"Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation","date":"2025-04-28","arxiv_id":"2504.19754","n_code_links":1,"syntology":null},{"paper":null,"slug":"security-bug-report-prediction-within-and","title":"Security Bug Report Prediction Within and Across Projects: A Comparative Study of BERT and Random Forest","date":"2025-04-28","arxiv_id":"2504.21037","n_code_links":0,"syntology":null},{"paper":"/paper/treehop-generate-and-filter-next-query","slug":"treehop-generate-and-filter-next-query","title":"TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering","date":"2025-04-28","arxiv_id":"2504.20114","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-speech-to-speech-dialogue-modeling","slug":"enhancing-speech-to-speech-dialogue-modeling","title":"Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation","date":"2025-04-27","arxiv_id":"2505.00028","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-influence-of-text-variation-on-user","title":"The Influence of Text Variation on User Engagement in Cross-Platform Content Sharing","date":"2025-04-26","arxiv_id":"2505.03769","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-model-and-package-for-german-colbert","title":"A model and package for German ColBERT","date":"2025-04-25","arxiv_id":"2504.20083","n_code_links":0,"syntology":null},{"paper":"/paper/smartfinrag-interactive-modularized-financial","slug":"smartfinrag-interactive-modularized-financial","title":"SMARTFinRAG: Interactive Modularized Financial RAG Benchmark","date":"2025-04-25","arxiv_id":"2504.18024","n_code_links":1,"syntology":null},{"paper":"/paper/a-rag-based-multi-agent-llm-system-for","slug":"a-rag-based-multi-agent-llm-system-for","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","date":"2025-04-24","arxiv_id":"2504.17200","n_code_links":1,"syntology":null},{"paper":"/paper/finbert-qa-financial-question-answering-with","slug":"finbert-qa-financial-question-answering-with","title":"FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models","date":"2025-04-24","arxiv_id":"2505.00725","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-graph-transformer-framework-for-gene","title":"A Novel Graph Transformer Framework for Gene Regulatory Network Inference","date":"2025-04-23","arxiv_id":"2504.16961","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-are-generative-large-language","title":"How Effective are Generative Large Language Models in Performing Requirements Classification?","date":"2025-04-23","arxiv_id":"2504.16768","n_code_links":0,"syntology":null},{"paper":"/paper/automated-bug-report-prioritization-in-large","slug":"automated-bug-report-prioritization-in-large","title":"Automated Bug Report Prioritization in Large Open-Source Projects","date":"2025-04-22","arxiv_id":"2504.15912","n_code_links":1,"syntology":null},{"paper":null,"slug":"citefix-enhancing-rag-accuracy-through-post","title":"CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction","date":"2025-04-22","arxiv_id":"2504.15629","n_code_links":0,"syntology":null},{"paper":null,"slug":"finder-financial-dataset-for-question","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","date":"2025-04-22","arxiv_id":"2504.15800","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounded-in-context-retrieval-based-method","title":"Grounded in Context: Retrieval-Based Method for Hallucination Detection","date":"2025-04-22","arxiv_id":"2504.15771","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-in-software-engineering","title":"Sentiment Analysis in Software Engineering: Evaluating Generative Pre-trained Transformers","date":"2025-04-22","arxiv_id":"2505.14692","n_code_links":0,"syntology":null},{"paper":null,"slug":"synergizing-rag-and-reasoning-a-systematic","title":"Synergizing RAG and Reasoning: A Systematic Review","date":"2025-04-22","arxiv_id":"2504.15909","n_code_links":0,"syntology":null},{"paper":"/paper/the-viability-of-crowdsourcing-for-rag","slug":"the-viability-of-crowdsourcing-for-rag","title":"The Viability of Crowdsourcing for RAG Evaluation","date":"2025-04-22","arxiv_id":"2504.15689","n_code_links":1,"syntology":null},{"paper":"/paper/alignrag-an-adaptable-framework-for-resolving","slug":"alignrag-an-adaptable-framework-for-resolving","title":"AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning","date":"2025-04-21","arxiv_id":"2504.14858","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["qqw-ing/rag-reasonalignment"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"leveraging-language-models-for-automated","title":"Leveraging Language Models for Automated Patient Record Linkage","date":"2025-04-21","arxiv_id":"2504.15261","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyrag-integrating-polyviews-into-retrieval","title":"POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications","date":"2025-04-21","arxiv_id":"2504.14917","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-evaluation-in","slug":"retrieval-augmented-generation-evaluation-in","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","date":"2025-04-21","arxiv_id":"2504.14891","n_code_links":1,"syntology":null},{"paper":null,"slug":"support-evaluation-for-the-trec-2024-rag","title":"Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges","date":"2025-04-21","arxiv_id":"2504.15205","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-great-nugget-recall-automating-fact","title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","date":"2025-04-21","arxiv_id":"2504.15068","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-synthetic-imputation-approach-generating","title":"The Synthetic Imputation Approach: Generating Optimal Synthetic Texts For Underrepresented Categories In Supervised Classification Tasks","date":"2025-04-21","arxiv_id":"2504.15160","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-linguistic-features-with","title":"Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings","date":"2025-04-20","arxiv_id":"2504.14766","n_code_links":0,"syntology":null},{"paper":null,"slug":"finsage-a-multi-aspect-rag-system-for","title":"FinSage: A Multi-aspect RAG System for Financial Filings Question Answering","date":"2025-04-20","arxiv_id":"2504.14493","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-ai-generated-questions-alignment","title":"Assessing AI-Generated Questions' Alignment with Cognitive Frameworks in Educational Assessment","date":"2025-04-19","arxiv_id":"2504.14232","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalrag-a-hybrid-rag-system-for-multilingual","title":"LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval","date":"2025-04-19","arxiv_id":"2504.16121","n_code_links":0,"syntology":null},{"paper":null,"slug":"cacheformer-high-attention-based-segment","title":"CacheFormer: High Attention-Based Segment Caching","date":"2025-04-18","arxiv_id":"2504.13981","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-embedding-based-clustering-to","title":"Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement","date":"2025-04-18","arxiv_id":"2504.14068","n_code_links":0,"syntology":null},{"paper":null,"slug":"cot-rag-integrating-chain-of-thought-and","title":"CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models","date":"2025-04-18","arxiv_id":"2504.13534","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-without-the-lag-interactive-debugging-for","title":"RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines","date":"2025-04-18","arxiv_id":"2504.13587","n_code_links":0,"syntology":null},{"paper":null,"slug":"secure-multifaceted-rag-for-enterprise-hybrid","title":"Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering","date":"2025-04-18","arxiv_id":"2504.13425","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-embedding-techniques-for-classification","title":"Word Embedding Techniques for Classification of Star Ratings","date":"2025-04-18","arxiv_id":"2504.13653","n_code_links":0,"syntology":null},{"paper":null,"slug":"accuracy-is-not-agreement-expert-aligned","title":"Accuracy is Not Agreement: Expert-Aligned Evaluation of Crash Narrative Classification Models","date":"2025-04-17","arxiv_id":"2504.13068","n_code_links":0,"syntology":null},{"paper":"/paper/cdf-rag-causal-dynamic-feedback-for-adaptive","slug":"cdf-rag-causal-dynamic-feedback-for-adaptive","title":"CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation","date":"2025-04-17","arxiv_id":"2504.12560","n_code_links":1,"syntology":null},{"paper":"/paper/estimating-optimal-context-length-for-hybrid","slug":"estimating-optimal-context-length-for-hybrid","title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","date":"2025-04-17","arxiv_id":"2504.12972","n_code_links":1,"syntology":null},{"paper":null,"slug":"freshstack-building-realistic-benchmarks-for","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","date":"2025-04-17","arxiv_id":"2504.13128","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructrag-leveraging-retrieval-augmented","title":"InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning","date":"2025-04-17","arxiv_id":"2504.13032","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-with-3","slug":"retrieval-augmented-generation-with-3","title":"Retrieval-Augmented Generation with Conflicting Evidence","date":"2025-04-17","arxiv_id":"2504.13079","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hannight/ramdocs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-visual-rag-pipeline-for-few-shot-fine","title":"A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification","date":"2025-04-16","arxiv_id":"2504.11838","n_code_links":0,"syntology":null},{"paper":null,"slug":"arcer-an-agentic-rag-for-the-automated","title":"ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges","date":"2025-04-16","arxiv_id":"2504.12143","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapping-controversies-using-artificial","title":"Mapping Controversies Using Artificial Intelligence: An Analysis of the Hamas-Israel Conflict on YouTube","date":"2025-04-16","arxiv_id":"2504.12177","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-feasibility-of-using-multimodal-llms","title":"On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks","date":"2025-04-16","arxiv_id":"2504.13209","n_code_links":0,"syntology":null},{"paper":null,"slug":"csplade-learned-sparse-retrieval-with-causal","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","date":"2025-04-15","arxiv_id":"2504.10816","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-distributed-retrieval-augmented","title":"Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance","date":"2025-04-15","arxiv_id":"2504.11197","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-role-of-kg-based-rag-in","title":"Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs","date":"2025-04-15","arxiv_id":"2504.10982","n_code_links":0,"syntology":null},{"paper":null,"slug":"intraoperative-perfusion-assessment-by","title":"Intraoperative perfusion assessment by continuous, low-latency hyperspectral light-field imaging: development, methodology, and clinical application","date":"2025-04-15","arxiv_id":"2504.10953","n_code_links":0,"syntology":null},{"paper":null,"slug":"layoutcot-unleashing-the-deep-reasoning","title":"LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation","date":"2025-04-15","arxiv_id":"2504.10829","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-automated-safety-requirements","title":"Towards Automated Safety Requirements Derivation Using Agent-based RAG","date":"2025-04-15","arxiv_id":"2504.11243","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-personalization-from-rag-to-agent","slug":"a-survey-of-personalization-from-rag-to-agent","title":"A Survey of Personalization: From RAG to Agent","date":"2025-04-14","arxiv_id":"2504.10147","n_code_links":1,"syntology":null},{"paper":null,"slug":"dior-adaptive-cognitive-detection-and","title":"DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation","date":"2025-04-14","arxiv_id":"2504.10198","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucination-detection-in-llms-via","title":"Hallucination Detection in LLMs via Topological Divergence on Attention Graphs","date":"2025-04-14","arxiv_id":"2504.10063","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmkb-rag-a-multi-modal-knowledge-based","title":"MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework","date":"2025-04-14","arxiv_id":"2504.10074","n_code_links":0,"syntology":null},{"paper":"/paper/rakg-document-level-retrieval-augmented","slug":"rakg-document-level-retrieval-augmented","title":"RAKG:Document-level Retrieval Augmented Knowledge Graph Construction","date":"2025-04-14","arxiv_id":"2504.09823","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-and-optimizing-multi-stage-ai","title":"Understanding and Optimizing Multi-Stage AI Inference Pipelines","date":"2025-04-14","arxiv_id":"2504.09775","n_code_links":0,"syntology":null},{"paper":null,"slug":"vdocrag-retrieval-augmented-generation-over","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","date":"2025-04-14","arxiv_id":"2504.09795","n_code_links":0,"syntology":null},{"paper":"/paper/xy-cut-advanced-layout-ordering-via","slug":"xy-cut-advanced-layout-ordering-via","title":"XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark","date":"2025-04-14","arxiv_id":"2504.10258","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlnet-a-firewall-for-rag-based-llm","title":"ControlNET: A Firewall for RAG-based LLM System","date":"2025-04-13","arxiv_id":"2504.09593","n_code_links":0,"syntology":null},{"paper":null,"slug":"hd-rag-retrieval-augmented-generation-for","title":"HD-RAG: Retrieval-Augmented Generation for Hybrid Documents Containing Text and Hierarchical Tables","date":"2025-04-13","arxiv_id":"2504.09554","n_code_links":0,"syntology":null},{"paper":"/paper/hm-rag-hierarchical-multi-agent-multimodal","slug":"hm-rag-hierarchical-multi-agent-multimodal","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","date":"2025-04-13","arxiv_id":"2504.12330","n_code_links":1,"syntology":null},{"paper":null,"slug":"heterag-a-heterogeneous-retrieval-augmented","title":"HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations","date":"2025-04-12","arxiv_id":"2504.10529","n_code_links":0,"syntology":null}],"record_sha256":"d6f659f8ae54caed57ae66edc7fc3c5e2d7203d39ae5a800429537c3905d1fc4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}