Abstract
Hallucination detection in large language and vision-language models is increasingly framed as selective prediction, where a detector assigns a confidence score and abstains when confidence is low. Unsupervised sampling detectors (Semantic Entropy, EigenScore) avoid labels but plateau in quality, while supervised probes (SAPLMA) attain stronger in-distribution scores yet degrade sharply when calibration labels are scarce. We recover the response manifold of an LLM as the density ridge of a kernel density estimate built on a six-dimensional kinematic feature map of hidden state generation trajectories. A test generation is scored by the negated Euclidean distance from its projected feature point to the nearest ridge vertex, yielding a low-dimensional geometric skeleton of the stochastic output distribution. We evaluate against Semantic Entropy, SAR, EigenScore, SAPLMA, and log-probability on seven QA benchmarks (HaluEval-QA, TriviaQA, GSM8K, POPE, ScienceQA, A-OKVQA) using nine text and vision LLMs in a deliberately label-scarce protocol ($n_{\text{cal}}{=}200$ queries, $N{=}5$ generations). Our ridge-based score beats on AUROC with 5-20 points gain, while demonstrating tempered degradation under calibration-label scarcity.
Abstract (translated)
URL
https://arxiv.org/abs/2606.10198
