RAG Evaluation

RAG: Retrieval-Augmented Generation

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 87% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 224

All topics

Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries
Jun 8, 2026Jianguo ZhuAdversarial Attacks on LLMs Indirect Prompt Injection
Chengdu University of Information Technology, Chengdu, China
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
Jun 7, 2026Jingyan Xu, Hong Shi, Yi Shan +4Retrieval-Augmented Generation LLM Grounding
DCST, Peking University · Beijing, China
Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
Jun 5, 2026Sevgi Yigit-SertRetrieval-Augmented Generation Knowledge Conflicts in Language Models
Computer Engineering Department, Ankara University, Golbasi Campus, 06830, Ankara, Turkey · Golbasi Campus, 06830, Ankara, Turkey
Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
Jun 5, 2026Sifei Meng, Dmitry IlvovskyCross-Encoder Reranking Retrieval-Augmented Generation
Faculty of Computer Science HSE University
Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions
Jun 4, 2026Haizhou XiaLLM Evaluation LLM Grounding
University of Western Ontario, Canada
Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
Jun 4, 2026Anuj Maharjan, Devinder Kaur, Richard MolyetRetrieval-Augmented Generation Adaptive RAG
Dept. of Electrical Engineering and Computer Science University of Toledo Toledo, OH, USA
Answer Presence Drives RAG Rewriting Gains
Jun 4, 2026Yuejie Li, Yueying Hua, Ke Yang +8Multi-Hop QA RAG Security
Ant Group
Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison
Jun 3, 2026Alejandro Lozano, Keiko Ihara, Ping-Hao Yang +13Text Summarization RAG Evaluation
Stanford University, Palo Alto, CA, USA · Department of Neurology, Mayo Clinic, Rochester, MN, USA · Department of Neurology, Dalhousie University, Halifax, Canada +8
QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples
Jun 3, 2026Mengao Zhang, Xiang Yang, Chang Liu +2Information Retrieval RAG Evaluation
Nanyang Technological University · Asian Institute of Digital Finance, National University of Singapore
MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning
Jun 3, 2026Qiyang Xie, Jialun Wu, Xinjie He +4Conversational Memory Retrieval-Augmented Generation
Northeastern University · Johns Hopkins University · Columbia University +1
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
Jun 2, 2026Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal +7Multimodal RAG Multimodal QA
JPMorgan Chase & Co. · Georgia Institute of Technology
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Jun 2, 2026Erfan Nourbakhsh, Rocky Slavin, Ke Yang +1Retrieval-Augmented Generation LLM Grounding
The University of Texas at San Antonio
Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA
Jun 2, 2026Mohamed Hesham Elganayni, Selim SalehCross-Encoder Reranking Feature Attribution
Technical University of Munich, Munich, Germany
Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit
Jun 1, 2026Nataraj Agaram Sundar, Tejas MorabiaDocument Chunking Retrieval-Augmented Generation
eBay Inc., San Jose, CA, USA
Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations
May 30, 2026Mateusz Śmigielski, Michał Rajkowski, Mateusz Zbrocki +5Document Chunking Retrieval-Augmented Generation
Department of Artificial Intelligence, Faculty of Information and Communication Technology, Wrocław University of Science and Technology, Wrocław 50-370, Poland
A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
May 29, 2026Bharath Simha Reddy MuthyamRetrieval-Augmented Generation Retrieval Robustness
Independent Researcher
Evaluating Factual Density in Multi-Source RAG: A Study in Medical AI Accuracy
May 29, 2026Michael R. DeMarcoInformation Retrieval RAG Evaluation
NexusAgentics / Ghost Audit
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
May 29, 2026Han Zhang, Zihao Tang, Xin Yu +8LLM Evaluation Memory-Augmented Language Models
Center for Applied Statistics, Renmin University of China · School of Statistics, Renmin University of China · Microsoft
On the impact of retrieved content representations in RAG Pipelines
May 29, 2026Jonathan J Ross, Bevan Koopman, Anton van der Vegt +1Retrieval-Augmented Generation RAG Evaluation
The University of Queensland · CSIRO / The University of Queensland
CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law
May 28, 2026Ethan Zhao, Maksym Taranukhin, Wei Cui +2Retrieval-Augmented Generation Legal QA
Department of Computer Science, University of British Columbia · Vector Institute · Peter A. Allard School of Law, University of British Columbia +1
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
May 28, 2026Songbo Hu, Yinhong Liu, Ej Zhou +5Spoken Dialogue Systems RAG Evaluation
Language Technology Lab, University of Cambridge, UK · Independent Researcher · School of Computation, Information and Technology, Technical University of Munich, Germany
RAISE: RAG Design as an Architecture Search Problem
May 28, 2026Zhen Chen, Yibing Liu, Weihao Xie +3RAG Evaluation Neural Architecture Search
City University of Hong Kong, Hong Kong SAR · Baidu Inc.
K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance
May 28, 2026Eunbyeol Cho, Yunseung Lee, Mirae Kim +3Retrieval-Augmented Generation Hallucination in Language Models
KAIST AI · Financial Tech Lab, KakaoBank Corp.
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG
May 27, 2026Yubo Li, Rema Padman, Ramayya KrishnanRetrieval-Augmented Generation Healthcare
Carnegie Mellon University
Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs
May 27, 2026Yongsik Seo, Wooseok Jeong, Eunyoung Kim +2Citation Verification RAG Evaluation
Department of Artificial Intelligence, Yonsei University · ParamitaAI · Department of Computer Science and Engineering, Konkuk University +2
Analyzing Quality-Latency-Resource Trade-offs in a Technical Documentation RAG Assistant Using LoRA Adaptation
May 27, 2026Evgenii Palnikov, Elizaveta GavrilovaLLM Inference Efficiency Retrieval-Augmented Generation
1HSE University
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
May 27, 2026Pin Qian, Su Wang, Xiaoyuan Wang +7Factual Consistency Evaluation Citation Verification
Carnegie Mellon University · Georgia Institute of Technology · Dartmouth College +3
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test
May 27, 2026Camilo Chacón Sartori, José H. GarcíaRetrieval-Augmented Generation LLM-as-a-Judge
Catalan Institute of Nanoscience and Nanotechnology (ICN2), CSIC and BIST, Campus UAB, Bellaterra, Barcelona, Spain
Separating Semantic Competition from Context Length in RAG Reading
May 26, 2026Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh +4Long-Context Retrieval Retrieval-Augmented Generation
Meta Platforms
Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
May 26, 2026Syed Huma ShahRetrieval-Augmented Generation RAG Security
Duke University · Syed Huma Shah$^*$

Jun 8, 2026, cs.CRJ/K move · Enter open · S save

Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries

Jianguo Zhu

Chengdu University of Information Technology, Chengdu, China

Adversarial Attacks on LLMs Indirect Prompt Injection RAG Security RAG Evaluation

Open paper AskPDF arXiv

Retrieval-augmented generation (RAG) systems often serialize user queries, retrieved documents, metadata, system labels, and task instructions into one natural-language prompt. We study a source-authority boundary failure in this design: attacker-authored retrieved text can impersonate metadata, provenance, authority, or disclosure-policy signals that appear control-relevant to the model. We call this pattern Document-Authored Control-Signal Impersonation (DACSI). DACSI is a non-imperative, metadata-like payload subclass within indirect prompt injection. Its central lesson is simple: document-authored labels are data, not policy. Command-style injection asks the model to ignore, override, or violate policy; DACSI asks whether untrusted document text can be misattributed as an authorized control signal when RAG prompt rendering collapses trusted and untrusted text into the same natural-language channel. We evaluate DACSI across six model settings, prompt-pressure levels, injection baselines, signal taxonomies, RAG-mediated pipelines, system-control probes, a source-authority attribution probe, and synthetic canary formats. We interpret the evidence by model regime rather than as six equal replications: DeepSeek V4 Pro and Qwen3.5-397B provide the cleanest positive lift, DeepSeek V4 Flash is a high-susceptibility setting, GPT-5.5 and Gemini 3.1 Pro Low are strong-boundary probes with selected residual risks, and GLM-4.7 is a saturated leakage boundary case. Across these regimes, DACSI warrants separate evaluation because it uses a command-free metadata/provenance/policy surface, follows a RAG-specific source-authority path, and responds to source/channel separation. The source-authority probe is behavioral attribution evidence, not proof of an internal mechanism.

Momentum

Related topics

Latest papers 224