一作SIGIR 2026Poster· Information Retrieval (Industry)
CSMAD: Hallucination Detection via Multi-Agent Debate with NLI-Verified Contradictory Statements
Swapnil Gupta · Akshay Verma · Khushi Gupta · Prateek Sircar · Deepak Gupta
摘要
Large Language Models (LLMs) are prone to hallucinations, producing fluent but factually incorrect statements. Recent multi-agent debate methods improve hallucination detection by jointly improving reasoning and decision-making. However, existing approaches either collaborate which amplifies shar...