Geometry-Aware Hallucination Detection in Large Language Models

ArXi:2601.06196v3 Announce Type: replace-cross Large language models (LLMs) frequently generate factually incorrect or uned content, commonly referred to as hallucinations. Prior work has explored decoding strategies, retrieval augmentation, and supervised fine-tuning for hallucination detection, while recent studies show that in-context learning (ICL) can substantially influence factual reliability. However, existing ICL nstration selection methods often rely on surface-level similarity heuristics and exhibit limited robustness across tasks and models.