Score: 0

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning

Published: January 5, 2026 | arXiv ID: 2601.02170v1

By: Haolang Lu , Minghui Pan , Ripeng Li and more

Potential Business Impact:

Finds fake answers in AI's thinking steps.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Page Count
26 pages

Category
Computer Science:
Artificial Intelligence