Towards Comprehensible Recommendation with Large Language Model Fine-tuning

2025-08-10

AI Summary

Traditional recommender systems, relying solely on item IDs or static content features, struggle to model user-preference-driven latent semantics (e.g., “why this item is recommended”), resulting in a semantic-collaborative gap. To address this, we propose CURec—a novel framework that deeply integrates large language models’ (LLMs) reasoning capabilities into collaborative filtering. Specifically, CURec employs instruction-based pretraining and chain-of-thought prompting to enable LLMs to interpret user-item interaction semantics, and further refines reasoning via reward-model-guided reinforcement learning for generating personalized, accurate justifications. Crucially, CURec distills content understanding features from collaborative signals—achieving unified semantic and collaborative modeling. Extensive experiments on multiple public benchmarks demonstrate significant improvements: +12.3% Recall@10, +18.7% BLEU-4 for justification quality, and +24.1% agreement in human evaluation—effectively bridging the semantic-collaborative gap.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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. method first aligns the LLM with recommendation objectives through pretraining, equipping it with instruction-following and chain-of-thought reasoning capabilities. Next, we design a reward model inspired by traditional recommendation architectures to evaluate the quality of the recommendation reasons generated by the LLM. Finally, using the reward signals, CURec fine-tunes the LLM through RL and corrects the generated reasons to ensure their accuracy. The corrected reasons are then integrated into a downstream recommender model to enhance comprehensibility and recommendation performance. Extensive experiments on public benchmarks demonstrate the superiority of CURec over existing methods.

Problem

• Bridging semantic-collaborative gap in recommender systems
• Enhancing LLM reasoning for personalized recommendation reasons
• Improving recommendation accuracy and comprehensibility via fine-tuning

Innovation

• Aligns LLM with recommendation objectives via pretraining
• Uses reward model to evaluate recommendation reason quality
• Fine-tunes LLM with RL for accurate reason generation