# Unsupervised Hallucination Detection by Inspecting Reasoning Processes

arXiv: https://arxiv.org/abs/2509.10004 · HTML: https://mlsanity.com/paper/2509.10004/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [LM-Polygraph: Uncertainty Estimation for Language Models](https://mlsanity.com/paper/2311.07383/) (2023)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models](https://mlsanity.com/paper/2403.06448/) (2024)
- [Effective Neural Topic Modeling with Embedding Clustering Regularization](https://mlsanity.com/paper/2306.04217/) (2023)
- [AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge](https://mlsanity.com/paper/2412.13670/) (2024)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)

## Built on by (most cited first, 5 of 5)

- [From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2606.27679/) (2026)
- [Learning Uncertainty from Sequential Internal Dispersion in Large Language Models](https://mlsanity.com/paper/2604.15741/) (2026)
- [Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2604.00445/) (2026)
- [No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents](https://mlsanity.com/paper/2605.12240/) (2026)
- [HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit](https://mlsanity.com/paper/2608.16353/) (2026)

## Abstract (arXiv)

Unsupervised hallucination detection aims to identify hallucinated content generated by large language models (LLMs) without relying on labeled data. While unsupervised methods have gained popularity by eliminating labor-intensive human annotations, they frequently rely on proxy signals unrelated to factual correctness. This misalignment biases detection probes toward superficial or non-truth-related aspects, limiting generalizability across datasets and scenarios. To overcome these limitations, we propose IRIS, an unsupervised hallucination detection framework, leveraging internal representations intrinsic to factual correctness. IRIS prompts the LLM to carefully verify the truthfulness of a given statement, and obtain its contextualized embedding as informative features for training. Meanwhile, the uncertainty of each response is considered a soft pseudolabel for truthfulness. Experimental results demonstrate that IRIS consistently outperforms existing unsupervised methods. Our approach is fully unsupervised, computationally low cost, and works well even with few training data, making it suitable for real-time detection.