# Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights

arXiv: https://arxiv.org/abs/2605.11330 · HTML: https://mlsanity.com/paper/2605.11330/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 15 of its 61 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 15 of 15)

- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases](https://mlsanity.com/paper/2403.10446/) (2024)
- [Unified Hallucination Detection for Multimodal Large Language Models](https://mlsanity.com/paper/2402.03190/) (2024)
- [The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://mlsanity.com/paper/2501.03200/) (2025)
- [SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes](https://mlsanity.com/paper/2504.11975/) (2025)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)
- [The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models](https://mlsanity.com/paper/2404.05904/) (2024)
- [LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals](https://mlsanity.com/paper/2509.21875/) (2025)
- [MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection](https://mlsanity.com/paper/2403.00964/) (2024)
- [SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection](https://mlsanity.com/paper/2404.06137/) (2024)

## Abstract (arXiv)

Hallucination, broadly referring to unfaithful, fabricated, or inconsistent content generated by LLMs, has wide-ranging implications. Therefore, a large body of effort has been devoted to detecting LLM hallucinations, as well as designing benchmark datasets for evaluating these detectors. In this work, we first establish a desiderata of properties for hallucination detection benchmarks (HDBs) to exhibit for effective evaluation. A critical look at existing HDBs through the lens of our desiderata reveals that none of them exhibits all the properties. We identify two largest gaps: (1) RAG-based grounded benchmarks with long context are severely lacking (partly because length impedes human annotation); and (2) Existing benchmarks do not make available realistic label noise for stress-testing detectors although real-world use-cases often grapple with label noise due to human or automated/weak annotation. To close these gaps, we build and open-source a new RAG-based HDB called T RIVIA+ that underwent a rigorous human annotation process. Notably, our benchmark exhibits all desirable properties including (1) T RIVIA+ contains samples with the longest context in the literature; and (2) we design and share four sets of noisy labels with different, both sample-dependent and sampleindependent, noise schemes. Finally, we perform experiments on RAG-based HDBs, including our T RIVIA+, using popular SOTA detectors that reveal new insights: (i) ample room remains for current detectors to reach the performance ceiling on RAG-based HDBs, (ii) the basic LLM-as-a-Judge baseline performs competitively, and (iii) label noise hinders detection performance. We expect that our findings, along with our proposed benchmark 1 , will motivate and foster needed research on hallucination detection for RAG-based tasks.