{"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/bert/papers/2","list_of":"/method/bert","method":"BERT","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":2,"pages_in_order":70,"rows_per_page":100,"rows":[101,200],"of":6938,"counts":{"archive_papers_tagged":6938,"with_a_code_link":2862,"where_syntology_ran_a_sample":640,"not_listed_spam_title":0,"listed":6938,"listed_where_code_ran":640,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":520,"every_run_a_failure_of_syntologys_instrument":120,"listed_with_a_run_with_no_instrument_failure":520,"listed_every_run_a_failure_of_syntologys_instrument":120,"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/bert","prev":"/method/bert","next":"/method/bert/papers/3","papers":[{"paper":"/paper/clueanchor-clue-anchored-knowledge-reasoning","slug":"clueanchor-clue-anchored-knowledge-reasoning","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation","date":"2025-05-30","arxiv_id":"2505.24388","n_code_links":1,"syntology":null},{"paper":null,"slug":"e-2graphrag-streamlining-graph-based-rag-for","title":"E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness","date":"2025-05-30","arxiv_id":"2505.24226","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-phenotyping-of-heart-failure","title":"Interpretable phenotyping of Heart Failure patients with Dutch discharge letters","date":"2025-05-30","arxiv_id":"2505.24619","n_code_links":0,"syntology":null},{"paper":null,"slug":"lpass-linear-probes-as-stepping-stones-for","title":"LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs","date":"2025-05-30","arxiv_id":"2505.24451","n_code_links":0,"syntology":null},{"paper":null,"slug":"realdrive-retrieval-augmented-driving-with","title":"RealDrive: Retrieval-Augmented Driving with Diffusion Models","date":"2025-05-30","arxiv_id":"2505.24808","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-between-semantic-and-user","title":"Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning","date":"2025-05-29","arxiv_id":"2505.23298","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-efficient-meta-models-for-evaluation-of","title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","date":"2025-05-29","arxiv_id":"2505.23299","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-ai-capabilities-in-detecting","slug":"evaluating-ai-capabilities-in-detecting","title":"Evaluating AI capabilities in detecting conspiracy theories on YouTube","date":"2025-05-29","arxiv_id":"2505.23570","n_code_links":1,"syntology":null},{"paper":null,"slug":"mcp-safety-training-learning-to-refuse","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","date":"2025-05-29","arxiv_id":"2505.23634","n_code_links":0,"syntology":null},{"paper":null,"slug":"mrag-elucidating-the-design-space-of-multi","title":"mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation","date":"2025-05-29","arxiv_id":"2505.24073","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-routing-for-retrieval-augmented","title":"Query Routing for Retrieval-Augmented Language Models","date":"2025-05-29","arxiv_id":"2505.23052","n_code_links":0,"syntology":null},{"paper":null,"slug":"agent-unirag-a-trainable-open-source-llm","title":"Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems","date":"2025-05-28","arxiv_id":"2505.22571","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-cloak-unveiling-chinese-cloaked","title":"Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon","date":"2025-05-28","arxiv_id":"2505.22184","n_code_links":0,"syntology":null},{"paper":"/paper/climate-finance-bench","slug":"climate-finance-bench","title":"Climate Finance Bench","date":"2025-05-28","arxiv_id":"2505.22752","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-memory-intelligence-a-foundational","title":"Contextual Memory Intelligence -- A Foundational Paradigm for Human-AI Collaboration and Reflective Generative AI Systems","date":"2025-05-28","arxiv_id":"2506.05370","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-rag-sub-dimensional-retrieval","slug":"cross-modal-rag-sub-dimensional-retrieval","title":"Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation","date":"2025-05-28","arxiv_id":"2505.21956","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-qa-efficiency-with-distilbert-fine","title":"Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs","date":"2025-05-28","arxiv_id":"2505.22937","n_code_links":0,"syntology":null},{"paper":"/paper/ragppi-rag-benchmark-for-protein-protein","slug":"ragppi-rag-benchmark-for-protein-protein","title":"RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery","date":"2025-05-28","arxiv_id":"2505.23823","n_code_links":1,"syntology":null},{"paper":null,"slug":"skewroute-training-free-llm-routing-for","title":"SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context","date":"2025-05-28","arxiv_id":"2505.23841","n_code_links":0,"syntology":null},{"paper":"/paper/vrag-rl-empower-vision-perception-based-rag","slug":"vrag-rl-empower-vision-perception-based-rag","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22019","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":["alibaba-nlp/vrag"],"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":null,"slug":"diagnosing-and-resolving-cloud-platform","title":"Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs","date":"2025-05-27","arxiv_id":"2505.21419","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-scaling-divide-and-conquer-via","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","date":"2025-05-27","arxiv_id":"2505.20625","n_code_links":0,"syntology":null},{"paper":null,"slug":"anveshana-a-new-benchmark-dataset-for-cross","title":"Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents","date":"2025-05-26","arxiv_id":"2505.19494","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-multimodal-knowledge-conflict","slug":"benchmarking-multimodal-knowledge-conflict","title":"Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models","date":"2025-05-26","arxiv_id":"2505.19509","n_code_links":1,"syntology":null},{"paper":"/paper/calibrating-pre-trained-language-classifiers","slug":"calibrating-pre-trained-language-classifiers","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","date":"2025-05-26","arxiv_id":"2505.19675","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-of-suicidal-risk-on-social-media-a","title":"Detection of Suicidal Risk on Social Media: A Hybrid Model","date":"2025-05-26","arxiv_id":"2505.23797","n_code_links":0,"syntology":null},{"paper":null,"slug":"dgrag-distributed-graph-based-retrieval","title":"DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems","date":"2025-05-26","arxiv_id":"2505.19847","n_code_links":0,"syntology":null},{"paper":null,"slug":"doctorrag-medical-rag-fusing-knowledge-with","title":"DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients","date":"2025-05-26","arxiv_id":"2505.19538","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-classification-in-context-in-spanish","title":"Emotion Classification In-Context in Spanish","date":"2025-05-26","arxiv_id":"2505.20571","n_code_links":0,"syntology":null},{"paper":"/paper/knowtrace-bootstrapping-iterative-retrieval","slug":"knowtrace-bootstrapping-iterative-retrieval","title":"KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing","date":"2025-05-26","arxiv_id":"2505.20245","n_code_links":1,"syntology":null},{"paper":null,"slug":"ma-rag-multi-agent-retrieval-augmented","title":"MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning","date":"2025-05-26","arxiv_id":"2505.20096","n_code_links":0,"syntology":null},{"paper":"/paper/neusym-rag-hybrid-neural-symbolic-retrieval","slug":"neusym-rag-hybrid-neural-symbolic-retrieval","title":"NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering","date":"2025-05-26","arxiv_id":"2505.19754","n_code_links":1,"syntology":null},{"paper":"/paper/r3-rag-learning-step-by-step-reasoning-and","slug":"r3-rag-learning-step-by-step-reasoning-and","title":"R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning","date":"2025-05-26","arxiv_id":"2505.23794","n_code_links":1,"syntology":null},{"paper":"/paper/syftr-pareto-optimal-generative-ai","slug":"syftr-pareto-optimal-generative-ai","title":"syftr: Pareto-Optimal Generative AI","date":"2025-05-26","arxiv_id":"2505.20266","n_code_links":1,"syntology":null},{"paper":"/paper/conventional-contrastive-learning-often-falls","slug":"conventional-contrastive-learning-often-falls","title":"Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data","date":"2025-05-25","arxiv_id":"2505.19274","n_code_links":1,"syntology":null},{"paper":"/paper/hermes-dravidianlangtech-2025-sentiment","slug":"hermes-dravidianlangtech-2025-sentiment","title":"Hermes@DravidianLangTech 2025: Sentiment Analysis of Dravidian Languages using XLM-RoBERTa","date":"2025-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/hypercube-rag-hypercube-based-retrieval","slug":"hypercube-rag-hypercube-based-retrieval","title":"Hypercube-RAG: Hypercube-Based Retrieval-Augmented Generation for In-domain Scientific Question-Answering","date":"2025-05-25","arxiv_id":"2505.19288","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-pedagogical-teacher-and-student","title":"Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style","date":"2025-05-25","arxiv_id":"2505.19173","n_code_links":0,"syntology":null},{"paper":"/paper/optimized-text-embedding-models-and","slug":"optimized-text-embedding-models-and","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","date":"2025-05-25","arxiv_id":"2505.19356","n_code_links":1,"syntology":null},{"paper":"/paper/poqd-performance-oriented-query-decomposer","slug":"poqd-performance-oriented-query-decomposer","title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","date":"2025-05-25","arxiv_id":"2505.19189","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pku-sds-lab/poqd-icml25"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"retrieval-augmented-generation-for-service","title":"Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking","date":"2025-05-25","arxiv_id":"2505.19310","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-llm-times-data","slug":"a-survey-of-llm-times-data","title":"A Survey of LLM $\\times$ DATA","date":"2025-05-24","arxiv_id":"2505.18458","n_code_links":2,"syntology":null},{"paper":null,"slug":"benchmarking-poisoning-attacks-against","title":"Benchmarking Poisoning Attacks against Retrieval-Augmented Generation","date":"2025-05-24","arxiv_id":"2505.18543","n_code_links":0,"syntology":null},{"paper":null,"slug":"brit-bidirectional-retrieval-over-unified","title":"BRIT: Bidirectional Retrieval over Unified Image-Text Graph","date":"2025-05-24","arxiv_id":"2505.18450","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-retrieval-augmented-generation-a","title":"Federated Retrieval-Augmented Generation: A Systematic Mapping Study","date":"2025-05-24","arxiv_id":"2505.18906","n_code_links":0,"syntology":null},{"paper":"/paper/gainrag-preference-alignment-in-retrieval","slug":"gainrag-preference-alignment-in-retrieval","title":"GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis","date":"2025-05-24","arxiv_id":"2505.18710","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-for-supply-chain-management","title":"LLMs for Supply Chain Management","date":"2025-05-24","arxiv_id":"2505.18597","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-for-performance-efficient-idiom-and","title":"Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT","date":"2025-05-24","arxiv_id":"2506.02005","n_code_links":0,"syntology":null},{"paper":"/paper/removal-of-hallucination-on-hallucination","slug":"removal-of-hallucination-on-hallucination","title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","date":"2025-05-24","arxiv_id":"2505.18581","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huenao/debate-augmented-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-silent-saboteur-imperceptible-adversarial","title":"The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems","date":"2025-05-24","arxiv_id":"2505.18583","n_code_links":0,"syntology":null},{"paper":null,"slug":"finragbench-v-a-benchmark-for-multimodal-rag","title":"FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain","date":"2025-05-23","arxiv_id":"2505.17471","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-probabilistic-generation-theory-a","title":"Multi-Scale Probabilistic Generation Theory: A Hierarchical Framework for Interpreting Large Language Models","date":"2025-05-23","arxiv_id":"2505.18244","n_code_links":0,"syntology":null},{"paper":null,"slug":"qwenlong-cprs-towards-infty-llms-with-dynamic","title":"QwenLong-CPRS: Towards $\\infty$-LLMs with Dynamic Context Optimization","date":"2025-05-23","arxiv_id":"2505.18092","n_code_links":0,"syntology":null},{"paper":null,"slug":"reqbrain-task-specific-instruction-tuning-of","title":"ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation","date":"2025-05-23","arxiv_id":"2505.17632","n_code_links":0,"syntology":null},{"paper":"/paper/resolving-conflicting-evidence-in-automated","slug":"resolving-conflicting-evidence-in-automated","title":"Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs","date":"2025-05-23","arxiv_id":"2505.17762","n_code_links":1,"syntology":null},{"paper":null,"slug":"align-grag-reasoning-guided-dual-alignment","title":"Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16237","n_code_links":0,"syntology":null},{"paper":"/paper/attributing-response-to-context-a-jensen","slug":"attributing-response-to-context-a-jensen","title":"Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16415","n_code_links":0,"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":null}},{"paper":null,"slug":"augmenting-llm-reasoning-with-dynamic-notes","title":"Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA","date":"2025-05-22","arxiv_id":"2505.16293","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-thought-poisoning-attacks-against-r1","title":"Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems","date":"2025-05-22","arxiv_id":"2505.16367","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-graph-model-cgm-a-graph-integrated-large","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","date":"2025-05-22","arxiv_id":"2505.16901","n_code_links":0,"syntology":null},{"paper":null,"slug":"dailyqa-a-benchmark-to-evaluate-web-retrieval","title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","date":"2025-05-22","arxiv_id":"2505.17162","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-generative-ai-for-story-point","title":"Multimodal Generative AI for Story Point Estimation in Software Development","date":"2025-05-22","arxiv_id":"2505.16290","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalizing-student-agent-interactions","title":"Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval Augmented Generation (RAG)","date":"2025-05-22","arxiv_id":"2505.17238","n_code_links":0,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-dynamic","slug":"r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17005","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rucaibox/r1-searcher-plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"search-wisely-mitigating-sub-optimal-agentic","title":"Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty","date":"2025-05-22","arxiv_id":"2505.17281","n_code_links":0,"syntology":null},{"paper":null,"slug":"voxrag-a-step-toward-transcription-free-rag","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering","date":"2025-05-22","arxiv_id":"2505.17326","n_code_links":0,"syntology":null},{"paper":"/paper/walk-retrieve-simple-yet-effective-zero-shot","slug":"walk-retrieve-simple-yet-effective-zero-shot","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","date":"2025-05-22","arxiv_id":"2505.16849","n_code_links":1,"syntology":null},{"paper":null,"slug":"after-retrieval-before-generation-enhancing","title":"After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in RAG","date":"2025-05-21","arxiv_id":"2505.17118","n_code_links":0,"syntology":null},{"paper":null,"slug":"br-taxqa-r-a-dataset-for-question-answering","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","date":"2025-05-21","arxiv_id":"2505.15916","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-vs-autoregressive-language-models-a","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","date":"2025-05-21","arxiv_id":"2505.15045","n_code_links":0,"syntology":null},{"paper":"/paper/hdlxgraph-bridging-large-language-models-and","slug":"hdlxgraph-bridging-large-language-models-and","title":"HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases","date":"2025-05-21","arxiv_id":"2505.15701","n_code_links":1,"syntology":null},{"paper":null,"slug":"infodeepseek-benchmarking-agentic-information","title":"InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation","date":"2025-05-21","arxiv_id":"2505.15872","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-foundation-models-for-multimodal","title":"Leveraging Foundation Models for Multimodal Graph-Based Action Recognition","date":"2025-05-21","arxiv_id":"2505.15192","n_code_links":0,"syntology":null},{"paper":null,"slug":"maxpoolbert-enhancing-bert-classification-via","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","date":"2025-05-21","arxiv_id":"2505.15696","n_code_links":0,"syntology":null},{"paper":null,"slug":"ranking-free-rag-replacing-re-ranking-with","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","date":"2025-05-21","arxiv_id":"2505.16014","n_code_links":0,"syntology":null},{"paper":null,"slug":"reranking-with-compressed-document","title":"Reranking with Compressed Document Representation","date":"2025-05-21","arxiv_id":"2505.15394","n_code_links":0,"syntology":null},{"paper":"/paper/silent-leaks-implicit-knowledge-extraction","slug":"silent-leaks-implicit-knowledge-extraction","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","date":"2025-05-21","arxiv_id":"2505.15420","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-llm-multiple-roles-a-unified-retrieval","title":"Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization","date":"2025-05-21","arxiv_id":"2505.15444","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-dataset-generation-for-knowledge","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","date":"2025-05-20","arxiv_id":"2505.14212","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-text-unveiling-privacy-vulnerabilities","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.13957","n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-by-question-conquer-by-agent-split-rag","title":"Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning","date":"2025-05-20","arxiv_id":"2505.13994","n_code_links":0,"syntology":null},{"paper":"/paper/informatics-for-food-processing","slug":"informatics-for-food-processing","title":"Informatics for Food Processing","date":"2025-05-20","arxiv_id":"2505.17087","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-rag-driven-anomaly-detection-and","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","date":"2025-05-20","arxiv_id":"2505.13828","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-bert-for-german-compound-semantics","title":"Probing BERT for German Compound Semantics","date":"2025-05-20","arxiv_id":"2505.14130","n_code_links":0,"syntology":null},{"paper":"/paper/process-vs-outcome-reward-which-is-better-for","slug":"process-vs-outcome-reward-which-is-better-for","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14069","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":["wlzhang2020/reasonrag"],"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/s3-you-don-t-need-that-much-data-to-train-a","slug":"s3-you-don-t-need-that-much-data-to-train-a","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","date":"2025-05-20","arxiv_id":"2505.14146","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":3,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pat-jj/s3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scan-semantic-document-layout-analysis-for","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.14381","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-adaptive-retrieval-augmented","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","date":"2025-05-19","arxiv_id":"2505.12731","n_code_links":0,"syntology":null},{"paper":null,"slug":"amaqa-a-metadata-based-qa-dataset-for-rag","title":"AMAQA: A Metadata-based QA Dataset for RAG Systems","date":"2025-05-19","arxiv_id":"2505.13557","n_code_links":0,"syntology":null},{"paper":"/paper/climate-research-domain-berts-pretraining","slug":"climate-research-domain-berts-pretraining","title":"Climate Research Domain BERTs: Pretraining, Adaptation, and Evaluation","date":"2025-05-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eavit-efficient-and-accurate-human-value","title":"EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs","date":"2025-05-19","arxiv_id":"2505.12792","n_code_links":0,"syntology":null},{"paper":"/paper/effective-and-transparent-rag-adaptive-reward","slug":"effective-and-transparent-rag-adaptive-reward","title":"Effective and Transparent RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability","date":"2025-05-19","arxiv_id":"2505.13258","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-rag-methods-for","title":"Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain","date":"2025-05-19","arxiv_id":"2505.13006","n_code_links":0,"syntology":null},{"paper":"/paper/know-or-not-a-library-for-evaluating-out-of","slug":"know-or-not-a-library-for-evaluating-out-of","title":"Know Or Not: a library for evaluating out-of-knowledge base robustness","date":"2025-05-19","arxiv_id":"2505.13545","n_code_links":1,"syntology":null},{"paper":"/paper/know3-rag-a-knowledge-aware-rag-framework","slug":"know3-rag-a-knowledge-aware-rag-framework","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","date":"2025-05-19","arxiv_id":"2505.12662","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation-for","title":"Optimizing Retrieval Augmented Generation for Object Constraint Language","date":"2025-05-19","arxiv_id":"2505.13129","n_code_links":0,"syntology":null},{"paper":null,"slug":"rar-setting-knowledge-tripwires-for-retrieval","title":"RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection","date":"2025-05-19","arxiv_id":"2505.13581","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-risk-assessment-using-multimodal","title":"Suicide Risk Assessment Using Multimodal Speech Features: A Study on the SW1 Challenge Dataset","date":"2025-05-19","arxiv_id":"2505.13069","n_code_links":0,"syntology":null},{"paper":"/paper/kgalign-joint-semantic-structural-knowledge","slug":"kgalign-joint-semantic-structural-knowledge","title":"KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection","date":"2025-05-18","arxiv_id":"2505.14714","n_code_links":1,"syntology":null},{"paper":"/paper/poisonarena-uncovering-competing-poisoning","slug":"poisonarena-uncovering-competing-poisoning","title":"PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation","date":"2025-05-18","arxiv_id":"2505.12574","n_code_links":1,"syntology":null}],"record_sha256":"dd6f9850adae2b7cb37dffc019c8faf4ac765ee94707bd7ef11ad0401cbfc2f1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}