当个性化误导：理解并缓解个性化大语言模型中的幻觉现象
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
AI总结：
本文提出FPPS方法，通过轻量级推理时间策略缓解个性化大语言模型中的事实性幻觉问题，并引入PFQABench基准评估事实性和个性化问答性能。
摘要：
个性化大型语言模型（LLM）通过调整模型行为来适应个体用户，以提高用户满意度，然而个性化可能会无意中扭曲事实推理。我们展示当个性化LLM面对事实性查询时，存在一种现象，即模型生成的答案与用户的先前历史一致，而不是客观真理，导致由个性化引起的幻觉现象，从而降低事实可靠性，并可能传播错误信念，这是由于个性化与事实表示之间的表征纠缠。为了解决这个问题，我们提出了Factuality-Preserving Personalized Steering（FPPS），一种轻量级的推理时间方法，该方法在保持个性化行为的同时缓解由个性化引起的事实扭曲。我们进一步引入PFQABench，第一个用于在个性化下联合评估事实性和个性化问答的基准。在多个LLM基础架构和个性化方法上的实验显示，FPPS显著提高了事实准确性，同时保持了个性化性能。
英文摘要：
Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.
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。
