PRISM通过四维度诊断，揭示大模型幻觉的根源。
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
- 将幻觉拆解为记忆、指令、推理三阶段四维度，实现精准定位。
- 在65个任务中测试24个模型，发现纠错常以牺牲其他能力为代价。
- 适合研究模型幻觉机制或提升模型可信度的开发者使用。
随着大语言模型从对话助手演变为能处理复杂任务的智能体，其在高风险场景中的应用日益广泛。然而，现有评估基准多依赖混合查询和输出层面评分，仅量化幻觉严重程度，难以揭示生成过程中幻觉产生的具体位置与原因。为此，本文将幻觉评估重构为诊断问题，提出PRISM——一个受控基准，将幻觉分解为四个维度：知识缺失、知识错误、推理错误和指令遵循错误，分别对应生成过程中的三个阶段（记忆、指令、推理）。PRISM包含跨65个任务的9,448个实例，支持细粒度、阶段感知的诊断评估。对24个主流开源与专有模型的评估发现，指令遵循、记忆检索与逻辑推理之间存在持续权衡，缓解策略常在改善某一维度的同时损害其他维度。我们期望PRISM能为理解大模型幻觉的具体机制提供框架，加速可信大模型的发展。
原文摘要 · Abstract (English)
As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others. We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models.
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。