AI RESEARCH
Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement
arXiv CS.CL
•
ArXi:2602.09486v2 Announce Type: replace Pretrained Large Language Models (LLMs) are prone to generating fluent yet factually incorrect text-a phenomenon known as hallucinations, undermining their reliability and utility in downstream tasks. We hypothesize that a generated text span's factuality is correlated with its representational instability across the model's internal layers. Based on this, we propose the CoCoA (Confusion and Consistency Aware) decoder, a novel