Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

Understand

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text.

• However, they often encounter the challenge of generating inaccurate or hallucinated content.
• This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the "snowballing" issue, especially in reasoning tasks.
• To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever).