通过他们的眼睛：基于注视点的个性化用户模拟调谐
Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation
AI总结：
本文提出FixATE方法，通过将视觉语言模型的视觉注意力与用户特定的注视模式对齐，提升推荐系统模拟的准确性，实验表明这种对齐能有效提高点击预测性能。
摘要：
大型语言模型（LLM）代理正被越来越多地部署为可扩展的用户模拟器，用于推荐系统评估。然而，现有模拟器通过文本或结构化元数据感知推荐，而非用户实际浏览的视觉界面——这是关键差距，因为注意力在推荐布局上既受视觉驱动又高度个性化。我们探讨是否能通过将视觉语言模型（VLM）的视觉注意力与用户特定的注视模式对齐来提升模拟保真度。分析一个真实世界的眼动追踪数据集，发现用户表现出稳定的个体注视模式，强烈预测点击行为。基于此发现，我们提出Fixation-Aligned Tuning for user Emulation（FixATE）。我们的方法首先通过可解释性操作符探测VLM的内部视觉注意力，获得与人类注视相似的槽级相关性分布，然后学习个性化软提示以引导模型的注意力朝向每个用户的特征注视模式。在三种可解释性基于的探测操作符和两种架构不同的VLM后端上进行实验，结果表明在注意力对齐和点击预测准确性方面都有一致的改进。这些结果表明，使模型“像用户一样看”是实现更忠实再现用户在推荐界面感知和行为的模拟器的可行路径。
英文摘要：
Large language model (LLM) agents are increasingly deployed as scalable user simulators for recommender system evaluation. Yet existing simulators perceive recommendations through text or structured metadata rather than the visual interfaces real users browse-a critical gap, since attention over recommendation layouts is both visually driven and highly personalized. We investigate whether aligning a vision-language model's (VLM's) visual attention with user-specific gaze patterns can improve simulation fidelity. Analysis of a real-world eye-tracking dataset collected in a carousel-based recommendation setting reveals that users exhibit stable individual gaze patterns strongly predictive of click behavior. Building on this finding, we propose Fixation-Aligned Tuning for user Emulation (FixATE). Our approach first probes the VLM's internal visual attention via interpretability operators to obtain a slot-level relevance distribution comparable with human fixation, and then learns personalized soft prompts to steer the model's attention toward each user's characteristic fixation pattern. Experiments across three interpretability-based probing operators and two architecturally distinct VLM backbones demonstrate consistent improvements in both attention alignment and click prediction accuracy. These results suggest that making the model "see like the user" is a viable path toward simulators that more faithfully reproduce how users perceive and act in recommendation interfaces.
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。
