# Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

arXiv: https://arxiv.org/abs/2403.06448 · HTML: https://mlsanity.com/paper/2403.06448/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 11 Mar 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer](https://mlsanity.com/paper/2212.02027/) (2022)
- [Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank](https://mlsanity.com/paper/2303.04710/) (2023)
- [THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval](https://mlsanity.com/paper/2305.06812/) (2023)
- [From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification](https://mlsanity.com/paper/2310.11675/) (2023)
- [Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval](https://mlsanity.com/paper/2312.10661/) (2023)
- [CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding](https://mlsanity.com/paper/2305.05393/) (2023)
- [THUIR2 at NTCIR-16 Session Search (SS) Task](https://mlsanity.com/paper/2307.00250/) (2023)
- [THUIR at WSDM Cup 2023 Task 1: Unbiased Learning to Rank](https://mlsanity.com/paper/2304.12650/) (2023)
- [THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment](https://mlsanity.com/paper/2305.06817/) (2023)
- [Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions](https://mlsanity.com/paper/2311.00333/) (2023)
- [Healthcare NER Models Using Language Model Pretraining](https://mlsanity.com/paper/1910.11241/) (2019)

## Built on by (most cited first, 30 of 86)

- [Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens](https://mlsanity.com/paper/2411.16724/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection](https://mlsanity.com/paper/2409.17504/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation](https://mlsanity.com/paper/2410.13640/) (2024)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://mlsanity.com/paper/2501.03200/) (2025)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [Skill Retrieval Augmentation for Agentic AI](https://mlsanity.com/paper/2604.24594/) (2026)
- [Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach](https://mlsanity.com/paper/2405.19648/) (2024)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Depth Gives a False Sense of Privacy: LLM Internal States Inversion](https://mlsanity.com/paper/2507.16372/) (2025)
- [Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads](https://mlsanity.com/paper/2505.20045/) (2025)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [Enhancing Hallucination Detection through Noise Injection](https://mlsanity.com/paper/2502.03799/) (2025)
- [LeKUBE: A Legal Knowledge Update BEnchmark](https://mlsanity.com/paper/2407.14192/) (2024)
- [FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs](https://mlsanity.com/paper/2410.02899/) (2024)
- [The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States](https://mlsanity.com/paper/2412.17056/) (2024)
- [EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs](https://mlsanity.com/paper/2509.15735/) (2025)
- [Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation](https://mlsanity.com/paper/2503.08216/) (2025)
- [Language Models Can Predict Their Own Behavior](https://mlsanity.com/paper/2502.13329/) (2025)
- [TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs](https://mlsanity.com/paper/2602.08048/) (2026)
- [A Survey of Automatic Hallucination Evaluation on Natural Language Generation](https://mlsanity.com/paper/2404.12041/) (2024)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method](https://mlsanity.com/paper/2601.20026/) (2026)
- [Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions](https://mlsanity.com/paper/2509.23782/) (2025)
- [FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG](https://mlsanity.com/paper/2601.05866/) (2026)
- [JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks](https://mlsanity.com/paper/2603.01291/) (2026)

## Abstract (arXiv)

Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research into detecting and mitigating hallucinations of LLMs. Previous studies have mainly concentrated on post-processing techniques for hallucination detection, which tend to be computationally intensive and limited in effectiveness due to their separation from the LLM's inference process. To overcome these limitations, we introduce MIND, an unsupervised training framework that leverages the internal states of LLMs for real-time hallucination detection without requiring manual annotations. Additionally, we present HELM, a new benchmark for evaluating hallucination detection across multiple LLMs, featuring diverse LLM outputs and the internal states of LLMs during their inference process. Our experiments demonstrate that MIND outperforms existing state-of-the-art methods in hallucination detection.