
DW
Dan Wilson, Mohamed Akrout
· 1 min read
ResearcharXiv cs.LG
Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction
arXiv:2605.05134v2 Announce Type: replace
Abstract: Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or external knowledge retrieval, we propose a new method that treats the LLM as a black-box dynamical system. By projecting LLM responses into a high-dimensional manifold via an embedding model, we characterize the resulting vector sequences as observable realizations of the model's latent state-space dynamics. Leveraging Koopman operator theory, we fit the transition operators for both factual and hallucinated regimes and define a differential residual score based on their respective prediction errors. This approach enables low-cost hallucination detection in a single-sample pass, avoiding the need for secondary sampling or external grounding. Extensive testing across three data benchmarks demonstrates that our method achieves state-of-the-art performance with reduced resource overhead.
Original source
This story was published by arXiv cs.LG and written by Dan Wilson, Mohamed Akrout. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


