减少复杂问答中的幻觉：使用基于简单图的检索增强生成（长版）
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
AI总结：
本研究提出一种轻量级图结构支持的检索增强生成系统，通过结合向量搜索和图查询工具，在复杂问答任务中将幻觉答案数量减半，并显著提升事实正确性的精确率和召回率。
摘要：
大型语言模型（LLMs）从根本上改变了自然语言处理的格局。尽管取得了这些进展，LLMs和基于LLM的系统仍然容易出现各种故障模式。检索增强生成（RAG）系统已成为一种常见的部署场景，旨在避免LLM“幻觉”信息的已知风险，并使模型能够对训练期间无法访问的专有信息进行推理和问答，而无需进行昂贵的模型微调。在这项工作中，我们探索了使用轻量级图结构（具有相对简单的图模式）通过专用工具集支持RAG子系统的想法。我们设计了一个基于英语维基百科文章精选子集的结构化数据集上的智能体系统，该系统配备了多种向量搜索和图查询工具，并评估了其在MoNaCo（一个具有挑战性的维基百科QA基准测试，涉及复杂查询回答任务）上的问题表现。我们的结果表明，引入基于图的工具可以显著提高事实正确性的精确率和召回率，将幻觉答案的数量减半，并在三个评估场景中实现了最高的细粒度真实性得分。所有这些都仅以适度的令牌使用增加为代价。
英文摘要：
Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing (NLP), although they remain susceptible to errors. Retrieval-augmented generation (RAG) systems have emerged as a common deployment scenario seeking to both avoid the well known risk of the LLM ``hallucinating'' information, and to enable reasoning and question answering over proprietary information that the LLM did not have access to during training without resorting to expensive model fine-tuning. In this work, we explore the idea of using a lightweight graph structure with a relatively simple graph schema, to support the RAG subsystem via a dedicated toolset. We design an agentic system with a variety of vector search and graph query tools operating over a structured dataset based on a curated subset of English Wikipedia articles, and evaluate its performance on questions from MoNaCo, a challenging Wikipedia based benchmark of complex question answering (QA) tasks. Our results show that the introduction of graph-based tools can significantly increase the precision and recall of factual correctness, can halve the number of hallucinated answers, and achieves the highest fine-grained truthfulness score among the three evaluated scenarios. All this with a modest increase in token usage.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
