Large Language Models (LLMs) are increasingly used to generate natural-language explanations in recommender systems, acting as explanation agents that reason over user behavior histories. While prior work has focused on explanation fluency and relevance under fixed inputs, the robustness of LLM-generated explanations to realistic user behavior noise remains largely unexplored. In real-world web platforms, interaction histories are inherently noisy due to accidental clicks, temporal inconsistencies, missing values, and evolving preferences, raising concerns about explanation stability and user trust. We present RobustExplain, the first systematic evaluation framework for measuring the robustness of LLM-generated recommendation explanations. RobustExplain introduces five realistic user behavior perturbations evaluated across multiple severity levels and a multi-dimensional robustness metric capturing semantic, keyword, structural, and length consistency. Our goal is to establish a principled, task-level evaluation framework and initial robustness baselines, rather than to provide a comprehensive leaderboard across all available LLMs. Experiments on four representative LLMs (7B--70B) show that current models exhibit only moderate robustness, with larger models achieving up to 8% higher stability. Our results establish the first robustness benchmarks for explanation agents and highlight robustness as a critical dimension for trustworthy, agent-driven recommender systems at web scale.

翻译：大型语言模型（LLM）在推荐系统中日益被用于生成自然语言解释，充当基于用户行为历史进行推理的解释代理。尽管先前研究主要关注固定输入下的解释流畅性与相关性，但LLM生成解释对现实用户行为噪声的鲁棒性仍亟待探索。在实际网络平台中，交互历史因误点击、时间不一致性、数据缺失及偏好演化而存在固有噪声，这引发了对解释稳定性与用户信任的担忧。本文提出RobustExplain——首个用于评估LLM生成推荐解释鲁棒性的系统化框架。该框架引入五种现实用户行为扰动（涵盖多严重等级）以及多维鲁棒性度量指标（涵盖语义一致性、关键词一致性、结构一致性与长度一致性）。本研究旨在建立原则性的任务级评估框架与初始鲁棒性基线，而非构建覆盖所有可用LLM的综合性排行榜。在四种代表性LLM（7B--70B参数规模）上的实验表明，当前模型仅具备中等鲁棒性，其中较大模型可获得最高8%的稳定性提升。本研究成果首次建立了解释代理的鲁棒性基准，并凸显了鲁棒性作为构建可信赖、代理驱动的网络级推荐系统的关键维度。