Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation
arXiv:2607.25366 · doi:10.1145/3770855.3817945
The paper introduces SharpRec, a method that merges large language models for cross-domain sequential recommendation by using sharpness-aware geometric alignment and preference salience activation to reduce knowledge conflicts and improve target domain performance.
Abstract
LLM-based Cross-Domain Sequential Recommendation (CDSR) leverages LLMs to enhance target performance via deep semantic reasoning, alleviating the dependency on overlapping users. Among LLM-based paradigms, model merging is particularly promising for multi-domain scenarios due to its superior scalability and flexibility in integrating diverse knowledge sources. However, our empirical investigations reveal two critical bottlenecks: (1) cross-domain knowledge conflict; and (2) performance saturation in multi-domain fusion. Our analysis attributes these phenomena to parameter-level misalignment and statistical homogenization during the merging process. To address these bottlenecks, we propose SharpRec, Sharpness-aware Model Merging with Salience Recovery for LLM-based CDSR, a framework designed to lift the performance upper bound of merged models. SharpRec incorporates two synergistic modules: Sharpness-aware Geometric Alignment to establish a stable geometric foundation for interference-free fusion; and Preference Salience Activation to effectively recover the distinctive features essential for bolstering target domain performance. Extensive experiments in both dual-domain and multi-domain scenarios demonstrate that SharpRec consistently outperforms state-of-the-art baselines.
Published in Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '26). 12 pages, 6 figures, 4 tables. Code available at https://github.com/muyiahhh/SharpRec