Towards Comprehensible Recommendation with Large Language Model Fine-tuning

Abstract

Recommender systems have become increasingly ubiquitous in daily life. While traditional recommendation approaches primarily rely on ID-based representations or item-side content features, they often fall short in capturing the underlying semantics aligned with user preferences (e.g., recommendation reasons for items), leading to a semantic-collaborative gap. Recently emerged LLM-based feature extraction approaches also face a key challenge: how to ensure that LLMs possess recommendation-aligned reasoning capabilities and can generate accurate, personalized reasons to mitigate the semantic-collaborative gap. To address these issues, we propose a novel Content Understanding from a Collaborative Perspective framework (CURec), which generates collaborative-aligned content features for more comprehensive recommendations. CURec first adapts the LLM with recommendation objectives through post-training, equipping it with instruction-following and chain-of-thought reasoning capabilities. Next, we use the LLM-generated features to train the recommender model. Then, we treat the user-item prediction scores produced by the trained recommender model as reward signals to guide RL-based refinement of the LLM, thereby improving the quality of generated reasons and pattern. The corrected reasons are directly integrated into the recommender model to enhance comprehensibility and recommendation performance. Extensive experiments on public benchmarks demonstrate the superiority of CURec over existing methods.