Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Guarantees on Dynamical System Distinguishability for LLM Token Generation
Mohamed Akrout, Dan Wilson
Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS…
cs.LG2026
Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction
Dan Wilson, Mohamed Akrout
Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computat…