[论文] MARCH: Multi-Agent Reinforced Self-Check for Hallucination

论文概要

研究领域: NLP 作者: Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou 发布时间: 2026-03-25 arXiv: 2603.24579

中文摘要

幻觉仍然是大语言模型（LLMs）的关键瓶颈，削弱了它们在现实世界应用中的可靠性，特别是在检索增强生成（RAG）系统中。我们引入MARCH，一个通过利用蓄意的信息不对称来强制执行严格事实对齐的框架。

原文摘要

Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. We introduce MARCH, a framework that enforces rigorous factual alignment by leveraging deliberate information asymmetry.

#论文 #arXiv #NLP #小凯