Who You Are Matters: Bridging Topics and Social Roles via LLM-Enhanced Logical Recommendation

2025-05-16

AI Summary

Existing recommender systems primarily model item topics and historical interactions, overlooking users’ social roles—a critical confounding factor influencing preference formation and evolution. Method: We propose TagCF, the first framework to explicitly model user social roles as logical confounders, integrating large language models (LLMs) for knowledge reasoning with graph neural networks (GNNs) to construct an interpretable topic–role logical graph. TagCF introduces a role-aware behavioral logic modeling task and enables cross-task transfer of user–item logical knowledge. Contribution/Results: Evaluated on multiple public and industrial datasets, TagCF significantly improves Recall@K and NDCG, particularly enhancing recommendation performance in cold-start and long-tail scenarios. The framework advances explainability and robustness by disentangling confounded social influences from topical and interactional signals.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• 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 filter contents/items valuable to users by inferring preferences from user features and historical behaviors. Mainstream approaches follow the learning-to-rank paradigm, which focus on discovering and modeling item topics (e.g., categories), and capturing user preferences on these topics based on historical interactions. However, this paradigm often neglects the modeling of user characteristics and their social roles, which are logical confounders influencing the correlated interest and user preference transition. To bridge this gap, we introduce the user role identification task and the behavioral logic modeling task that aim to explicitly model user roles and learn the logical relations between item topics and user social roles. We show that it is possible to explicitly solve these tasks through an efficient integration framework of Large Language Model (LLM) and recommendation systems, for which we propose TagCF. On the one hand, the exploitation of the LLM's world knowledge and logic inference ability produces a virtual logic graph that reveals dynamic and expressive knowledge of users, augmenting the recommendation performance. On the other hand, the user role aligns the user behavioral logic with the observed user feedback, refining our understanding of user behaviors. Additionally, we also show that the extracted user-item logic graph is empirically a general knowledge that can benefit a wide range of recommendation tasks, and conduct experiments on industrial and several public datasets as verification.

Problem

• Modeling user social roles and characteristics in recommendations
• Bridging item topics and user roles via logical relations
• Enhancing recommendations with LLM-generated dynamic logic graphs

Innovation

• LLM-enhanced framework models user roles
• Virtual logic graph augments recommendation performance
• User role aligns behavioral logic with feedback