无幻觉的自动问答生成用于直观学习
Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning
AI总结：
本文提出无幻觉的多代理生成框架，通过结构化协作减少教育内容中的幻觉，提升问答生成的准确性与教育价值。
摘要：
大型语言模型（LLMs）中的幻觉，定义为流畅但错误或不连贯的输出，对自动生成教育性多项选择题（MCQs）构成了重大挑战。我们识别出MCQ生成中的四种关键幻觉类型：推理不一致、不可解性、事实错误和数学错误。为解决这一问题，我们提出了一种无幻觉的多代理生成框架，将MCQ生成分解为可验证的离散阶段。我们的框架利用基于规则和LLM的检测代理，以及幻觉评分指标来优化问题质量。我们重新定义MCQ生成为一个优化任务，旨在最小化幻觉风险，同时最大化有效性、可回答性和成本效率。我们还引入了代理主导的细化过程，利用反事实推理和思维链（CoT）来迭代改进问题生成中的幻觉。我们评估了一组与AP对齐的STEM问题样本，其中我们的系统将幻觉率降低了超过90%，同时保持了问题的教育价值和风格。我们的结果表明，结构化的多代理协作可以大规模缓解教育内容创作中的幻觉，为更可靠的LLM驱动学习工具铺平道路。
英文摘要：
Hallucinations in large language models (LLMs), defined as fluent yet incorrect or incoherent outputs, pose a significant challenge to the automatic generation of educational multiple-choice questions (MCQs). We identified four key hallucination types in MCQ generation: reasoning inconsistencies, insolvability, factual errors, and mathematical errors. To address this, we propose a hallucination-free multi-agent generation framework that breaks down MCQ generation into discrete, verifiable stages. Our framework utilizes both rule-based and LLM-based detection agents, as well as hallucination scoring metrics to optimize question quality. We redefined MCQ generation as an optimization task minimizing hallucination risk while maximizing validity, answerability, and cost-efficiency. We also introduce an agent-led refinement process that uses counterfactual reasoning and chain-of-thought (CoT) to iteratively improve hallucination in question generation. We evaluated a sample of AP- aligned STEM questions, where our system reduced hallucination rates by over 90% compared to baseline generation while preserving the educational value and style of questions. Our results demonstrate that structured multi-agent collaboration can mitigate hallucinations in educational content creation at scale, paving the way for more reliable LLM-powered learning tools.
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。
