What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context

arXiv:2506.02261v3 Announce Type: replace-cross Abstract: What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approaches largely rely on binary pairwise comparisons, overlooking two critical factors: preference intensity (the structured strength of affinity or aversion) and temporal context (the extent to which recent interactions better reflect a user's current intent). Through controlled experiments, we show that leveraging comprehensive feedback with structured preference signals substantially improves recommendation performance, indicating that binary modeling discards essential information. Motivated by these findings, we propose RecPO, a unified preference optimization framework that maps both explicit and implicit feedback into a common preference signal and constructs adaptive reward margins that jointly account for preference intensity and interaction recency. Experiments across five datasets show that RecPO consistently outperforms state-of-the-art baselines while exhibiting behavioral patterns aligned with human decision-making, including favoring immediate satisfaction, maintaining preference coherence, and avoiding dispreferred items. Our results highlight that preference intensity and temporal context are fundamental ingredients for effective LLM-based recommendation.

Related

• Information-Consistent Language Model Recommendations through Group Relative Policy Optimization
• Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
• Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
• GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

Source: arXiv cs.LG | 2026-04-20