Streaming Hallucination Detection in Long Chain-of-Thought Reasoning

ACL ARR 2026 January Submission3791 Authors

Keywords: Large Language Models, Hallucination Detection, Chain-of-Thought Reasoning

Abstract:

Long chain-of-thought (CoT) reasoning improves the performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps.
We suggest that hallucination in long CoT reasoning is better understood as an evolving latent state rather than a one-off erroneous event.
Accordingly, we treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level hallucination signal that tracks the global evolution of the reasoning state over the entire trajectory.
Overall, our approach enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: Interpretability and Analysis of Models for NLP, Language Modeling

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 3791