大语言模型中的幻觉检测与缓解
Hallucination Detection and Mitigation in Large Language Models
AI总结：
本文提出了一种系统化的框架，通过分层架构和闭环反馈机制，提升大语言模型在金融等高风险领域的可靠性，减少幻觉问题。
摘要：
大语言模型（LLMs）和大推理模型（LRMs）在金融和法律等高风险领域具有变革性潜力，但其倾向于产生事实性错误或未经支持的内容，这构成了关键的可靠性风险。本文介绍了一种全面的操作框架，用于幻觉管理，该框架基于由根本原因意识驱动的持续改进循环。我们把幻觉来源分为模型、数据和上下文相关因素，允许针对特定因素进行干预，而非通用解决方案。该框架整合了多种检测方法（例如不确定性估计、推理一致性）与分层缓解策略（例如知识 grounding、置信度校准）。我们通过分层架构和一个金融数据提取案例研究展示了其应用，其中模型、上下文和数据层级形成闭环反馈循环，以实现逐步的可靠性提升。这种方法提供了一种系统化、可扩展的方法，用于在受监管环境中构建可信的生成式人工智能系统。
英文摘要：
Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk. This paper introduces a comprehensive operational framework for hallucination management, built on a continuous improvement cycle driven by root cause awareness. We categorize hallucination sources into model, data, and context-related factors, allowing targeted interventions over generic fixes. The framework integrates multi-faceted detection methods (e.g., uncertainty estimation, reasoning consistency) with stratified mitigation strategies (e.g., knowledge grounding, confidence calibration). We demonstrate its application through a tiered architecture and a financial data extraction case study, where model, context, and data tiers form a closed feedback loop for progressive reliability enhancement. This approach provides a systematic, scalable methodology for building trustworthy generative AI systems in regulated environments.
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。
