提出一套系统化框架，解决大模型幻觉问题。
Hallucination Detection and Mitigation in Large Language Models
- 按模型、数据、上下文三类归因，精准定位幻觉根源。
- 融合不确定性估计与推理一致性检测，提升识别率。
- 适合金融、法律等高风险场景的可信AI建设。
大语言模型（LLMs）和大推理模型（LRMs）在金融、法律等高风险领域具有变革潜力，但其生成虚假或无支持内容的幻觉问题严重威胁可靠性。本文提出一个基于根因认知的持续改进框架，将幻觉来源分为模型、数据和上下文三类，实现针对性干预而非通用修复。框架整合多维度检测方法（如不确定性估计、推理一致性）与分层缓解策略（如知识锚定、置信度校准）。通过分层架构与金融数据提取案例验证，模型、上下文与数据三层形成闭环反馈，逐步提升系统可靠性。该方法为受监管环境中的可信生成式AI提供系统化、可扩展的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。