Hallucination in RAG

RAG: Retrieval-Augmented Generation

Follow this topic Ask about this topic

Latest papers

19 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

When Does Uncertainty Measure RAG Hallucination Risk?
Oct 15, 2026Rajeel Ahmad Ansari, Tautik AgrahariHallucination in RAG LLM Hallucination Detection
Independent Researcher, Delhi, India · Independent Researcher, Bengaluru, India
Grounding Probes: Generator-Independent Hallucination Detection from Observer Model Hidden States
Oct 3, 2026Michael Rathmayr, Ádám Kovács, Gábor RecskiHallucination in RAG LLM Grounding
TU Wien, Austria · KR Labs
Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
Aug 29, 2026Sai Krishna Reddy Mulakkayala, Niki van Stein, Aske PlaatHallucination in RAG LLM Hallucination Mitigation
LIACS, Leiden University, Leiden, The Netherlands
Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries
Aug 26, 2026Alden Do Rosario, Hussein Younes, Felipe PiresHallucination in RAG Retrieval-Augmented Generation
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
Aug 18, 2026Md. Faiyaz Abdullah SayeediLong-Context Reasoning in Language Models Hallucination in RAG
BRAC University, Bangladesh
SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems
Jul 20, 2026Julia Belikova, Rauf Parchiev, Mikhail Filimonov +3Retrieval-Augmented Generation LLM Answer Verification
Sber AI Lab
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning
Jul 12, 2026Fengji Zhang, Tianyu Fan, Yuxiang Zheng +4Question Answering RL for LLM Agents
City University of Hong Kong · Alibaba Group
Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)
Jul 5, 2026Mohamed Aly BoukeRetrieval-Augmented Generation LLM Grounding
Centre for Intelligent Cloud Computing, CoE for Advanced Cloud, Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia
Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents
Jul 1, 2026Ádám Kovács, Bowei He, Xue Liu +3LLM Grounding Hallucination Detection
KR Labs · MBZUAI · McGill University +1
CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations
Jun 30, 2026Kazuaki Furumai, Shuichiro Haruta, Kazunori Matsumoto +1Retrieval-Augmented Generation LLM Hallucination Detection
KDDI Research, Inc.
Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection
Jun 4, 2026Jianru ShenRetrieval-Augmented Generation Hallucination in Language Models
University of Montana Missoula, MT, USA
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Jun 4, 2026Christopher J. Wedge, Joshua Stutter, Danny Dixon +1Multi-Hop QA Tool-Augmented Language Model Agents
National Innovation Centre for Data, Newcastle University
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 RAG
KAIST AI · Financial Tech Lab, KakaoBank Corp.
From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
May 8, 2026Jiaju Han, Chao Li, Chengyin Hu +8Multimodal RAG Retrieval-Augmented Generation
China University of Petroleum, Beijing at Karamay, Karamay, Xinjiang 834000, China
RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
Apr 17, 2026Fabian Ridder, Laurin Lessel, Malte SchillingHallucination in Language Models RAG Robustness
Computer Science Department, University of Münster, Münster, Germany
Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
Apr 10, 2026Passant Elchafei, Monorama Swain, Shahed Masoudian +1Hallucination in RAG RAG Evaluation
Johannes Kepler University Linz, Institute of Computational Perception, Linz, Austria · Linz Institute of Technology, Artificial Intelligence Lab, Austria
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Apr 9, 2026Zhengyi Zhao, Shubo Zhang, Zezhong Wang +7Hallucination in RAG Retrieval-Augmented Generation
The Chinese University of Hong Kong · Ministry of Education Key Laboratory of High Confidence Software Technologies, CUHK · University of International Relations +2
Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG
Mar 29, 2026Boxi Yu, Yuzhong Zhang, Liting Lin +2Hallucination in RAG LLM Hallucination Detection
Lero, the Research Ireland Centre for Software, University of Limerick, Ireland · The Chinese University of Hong Kong, Shenzhen, China · University of Ottawa, Canada +1
Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
Mar 28, 2026Zequn Xie, Zhengyang SunHallucination in RAG LLM Hallucination Mitigation
Polytechnic Institute, Zhejiang University, Hangzhou, China · School of Computer Science and Technology, Xinjiang University, Urumqi, China

Oct 15, 2026J/K move · Enter open · S save

When Does Uncertainty Measure RAG Hallucination Risk?

Rajeel Ahmad Ansari, Tautik Agrahari

Independent Researcher, Delhi, India · Independent Researcher, Bengaluru, India

Hallucination in RAG LLM Hallucination Detection Retrieval-Augmented Generation RAG Evaluation Uncertainty Calibration

Open paper AskPDF arXiv

Uncertainty can measure hallucination risk in retrieval-augmented generation (RAG), but only when retrieved evidence constrains the answer. When evidence is present, unsupported factual claims become less likely; when retrieval coverage is poor, the model can answer from internal knowledge and assign high probability to unsupported claims. We test this across four instruction-tuned models on HotpotQA and SQuAD. After matching faithful and hallucinated answers within word-count bins, length-only classifiers fall near chance, while perplexity reaches 0.81--0.91 AUROC on targeted unsupported edits. Varying retrieval depth shows why the score changes meaning: detection can weaken with only the top-ranked passage, then recover after adding a second passage. A combined uncertainty and semantic-drift score improves calibration, and measurements remain above chance on RAGTruth QA. Results support a conditional view of uncertainty as a useful measure of RAG hallucination risk.