# ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs

arXiv: https://arxiv.org/abs/2507.16488 · HTML: https://mlsanity.com/paper/2507.16488/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 12 of 12)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)

## Built on by (most cited first, 30 of 32)

- [AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents](https://mlsanity.com/paper/2601.06818/) (2026)
- [HALT: Hallucination Assessment via Log-probs as Time series](https://mlsanity.com/paper/2602.02888/) (2026)
- [When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents](https://mlsanity.com/paper/2606.22864/) (2026)
- [Gradient-Stable Attention Heads Signal LLM Correctness](https://mlsanity.com/paper/2602.13699/) (2026)
- [A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models](https://mlsanity.com/paper/2606.19868/) (2026)
- [CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models](https://mlsanity.com/paper/2601.14310/) (2026)
- [Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection](https://mlsanity.com/paper/2601.19245/) (2026)
- [RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration](https://mlsanity.com/paper/2604.15945/) (2026)
- [HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models](https://mlsanity.com/paper/2604.26139/) (2026)
- [TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection](https://mlsanity.com/paper/2606.01033/) (2026)
- [OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios](https://mlsanity.com/paper/2606.06959/) (2026)
- [The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice](https://mlsanity.com/paper/2608.28930/) (2026)
- [Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models](https://mlsanity.com/paper/2508.07753/) (2025)
- [CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models](https://mlsanity.com/paper/2604.11087/) (2026)
- [Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments](https://mlsanity.com/paper/2605.03971/) (2026)
- [Enabling Performant and Flexible Model-Internal Observability for LLM Inference](https://mlsanity.com/paper/2605.11093/) (2026)
- [Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution](https://mlsanity.com/paper/2606.05486/) (2026)
- [Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2606.19404/) (2026)
- [CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations](https://mlsanity.com/paper/2606.31033/) (2026)
- [Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection](https://mlsanity.com/paper/2607.16643/) (2026)
- [The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Shared Category Geometry in Small Language Models](https://mlsanity.com/paper/2607.16741/) (2026)
- [DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models](https://mlsanity.com/paper/2608.03411/) (2026)
- [Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2608.27165/) (2026)
- [IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals](https://mlsanity.com/paper/2609.01375/) (2026)
- [When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs](https://mlsanity.com/paper/2609.15106/) (2026)
- [LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models](https://mlsanity.com/paper/2609.27220/) (2026)
- [Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons](https://mlsanity.com/paper/2609.29781/) (2026)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)
- [MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems](https://mlsanity.com/paper/2609.36556/) (2026)
- [Locating Answer-Correctness Signals in Frozen Large Language Models](https://mlsanity.com/paper/2609.37700/) (2026)

## Abstract (arXiv)

Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability. Existing hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations, overlooking their dynamic evolution across layers, which limits efficacy. To address this limitation, we shift the focus to the hidden state update process and introduce a novel metric, the ICR Score (Information Contribution to Residual Stream), which quantifies the contribution of modules to the hidden states' update. We empirically validate that the ICR Score is effective and reliable in distinguishing hallucinations. Building on these insights, we propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states. Experimental results show that the ICR Probe achieves superior performance with significantly fewer parameters. Furthermore, ablation studies and case analyses offer deeper insights into the underlying mechanism of this method, improving its interpretability.