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

TL;DR

This paper investigates how large language models (LLMs) can be improved for sequential recommendation by incorporating preference intensity and temporal context, leading to a new framework called RecPO.

Contribution

It introduces RecPO, a unified preference optimization framework that leverages structured feedback and adaptive reward margins to enhance recommendation performance.

Findings

RecPO outperforms state-of-the-art baselines across five datasets.

Structured preference signals significantly improve recommendation accuracy.

Behavioral patterns of RecPO align with human decision-making principles.

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.