# Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

arXiv: https://arxiv.org/abs/2505.20045 · HTML: https://mlsanity.com/paper/2505.20045/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 30 of 45)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models](https://mlsanity.com/paper/2307.01379/) (2023)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)

## Built on by (most cited first, 16 of 16)

- [Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning](https://mlsanity.com/paper/2509.02401/) (2025)
- [Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation](https://mlsanity.com/paper/2510.02279/) (2025)
- [Uncertainty Propagation in LLM-Based Systems](https://mlsanity.com/paper/2604.23505/) (2026)
- [Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering](https://mlsanity.com/paper/2601.17284/) (2026)
- [Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention](https://mlsanity.com/paper/2602.18145/) (2026)
- [The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2606.22792/) (2026)
- [Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval](https://mlsanity.com/paper/2603.05471/) (2026)
- [Learning Uncertainty from Sequential Internal Dispersion in Large Language Models](https://mlsanity.com/paper/2604.15741/) (2026)
- [Evolutionary Search for Automated Design of Uncertainty Quantification Methods](https://mlsanity.com/paper/2604.03473/) (2026)
- [Useful Features, Backward Scores: OOD in Language-Model Trajectories](https://mlsanity.com/paper/2605.00269/) (2026)
- [Uncertainty Quantification for Large Language Diffusion Models](https://mlsanity.com/paper/2605.14570/) (2026)
- [How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?](https://mlsanity.com/paper/2605.27016/) (2026)
- [Integrating Local and Global Entropy for Uncertainty Quantification in LLMs](https://mlsanity.com/paper/2606.09875/) (2026)
- [SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems](https://mlsanity.com/paper/2608.00033/) (2026)
- [ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps](https://mlsanity.com/paper/2609.11498/) (2026)
- [Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization](https://mlsanity.com/paper/2609.14839/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ) offers a promising way to mitigate this issue, but most existing methods are computationally intensive and/or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain "uncertainty-aware" attention heads tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve datasets spanning question answering, summarization, and translation across nine different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it incurs minimal overhead, requiring less than 1% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.