PRISM：探究语言模型幻觉中的推理、指令和来源记忆
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
AI总结：
PRISM通过四个维度分析语言模型幻觉，提供细粒度诊断评估，揭示不同模型在指令遵循、记忆检索和逻辑推理上的权衡。
摘要：
随着大型语言模型（LLMs）从对话助手发展为能处理复杂任务的代理，它们越来越多地应用于高风险领域。然而，现有基准测试主要依赖混合查询和后验评估，输出级评分，虽然能量化幻觉严重性，但对幻觉在生成流程中出现的位置和原因缺乏深入洞察。因此，我们将幻觉评估重新定义为诊断问题，并提出PRISM，一个受控基准测试，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，基于生成的三个阶段（记忆、指令和推理）。PRISM包含9,448个实例，覆盖65个任务，并支持细粒度、阶段意识的诊断评估。评估24种主流开源和专有LLMs，我们揭示了在指令遵循、记忆检索和逻辑推理之间的持续权衡，显示缓解策略通常在改善特定维度的同时牺牲其他方面。我们希望PRISM能为理解LLMs幻觉的具体机制提供框架，最终加速可信大型语言模型的发展。
英文摘要：
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.
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。
