Logprobs Know Uncertainty: Fighting LLM Hallucinations

Large Language Models (LLMs) excel in text generation but remain prone to hallucinations. Existing mitigation methods like Retrieval-Augmented Generation (RAG) and self-assessment face efficiency and bias limitations. We propose a novel logprob-based framework that proactively quantifies model uncertainty through two innovations: (1) integrating antonym candidates in token predictions, and (2) deriving uncertainty metrics from token-level logprobs. Experiments demonstrate our method effectively suppresses hallucinations while maintaining computational efficiency and transparency, offering a scalable solution for reliable LLM outputs.