mlsanityData to 7 Oct 2026

Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?

arXiv 2503.21157 ↗First posted 27 Mar 2025cs.LGcited by 3

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

This article surveys Evaluation models to automatically detect hallucinations in Retrieval-Augmented Generation (RAG), and presents a comprehensive benchmark of their performance across six RAG applications. Methods included in our study include: LLM-as-a-Judge, Prometheus, Lynx, the Hughes Hallucination Evaluation Model (HHEM), and the Trustworthy Language Model (TLM). These approaches are all reference-free, requiring no ground-truth answers/labels to catch incorrect LLM responses. Our study reveals that, across diverse RAG applications, some of these approaches consistently detect incorrect RAG responses with high precision/recall.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 6 of its 12 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

6 of 12 references.

References · 6

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2019ELI5: Long Form Question Answeringcited by 567
  4. 2024Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Modelscited by 431
  5. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  6. 2023Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Studycited by 85

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflectioncited by 6
  2. 2025HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Modelscited by 5
  3. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
  2. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
  3. 2025Osiris: A Lightweight Open-Source Hallucination Detection System
  4. 2024Lynx: An Open Source Hallucination Evaluation Model
  5. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  6. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
  7. 2026Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights
  8. 2026Mitigating Hallucination on Hallucination in RAG via Ensemble Voting