Leveraging LLMs for Influence Path Planning in Proactive Recommendation

2024-09-07

AI Summary

To address interest narrowing and information filtering in recommender systems, this paper proposes an LLM-driven influence path planning method that guides users from their historical interests to target items via semantically coherent recommendation sequences. Unlike existing influence-based recommendation systems (IRS), which suffer from insufficient target coverage and fragmented paths, our approach introduces the first LLM-based influence path generation framework, integrating prompt engineering, user interest transition modeling, and interpretable path generation. We further design novel evaluation metrics and a user simulator to ensure both target reachability and semantic coherence. Experimental results demonstrate significant improvements over conventional sequential models: +32.7% in path coherence and +28.4% in user acceptance rate. This work establishes a new paradigm for explainable and controllable interest expansion in recommendation.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

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: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Recommender systems are pivotal in Internet social platforms, yet they often cater to users' historical interests, leading to critical issues like echo chambers. To broaden user horizons, proactive recommender systems aim to guide user interest to gradually like a target item beyond historical interests through an influence path,i.e., a sequence of recommended items. As a representative, Influential Recommender System (IRS) designs a sequential model for influence path planning but faces issues of lacking target item inclusion and path coherence. To address the issues, we leverage the advanced planning capabilities of Large Language Models (LLMs) and propose an LLM-based Influence Path Planning (LLM-IPP) method. LLM-IPP generates coherent and effective influence paths by capturing user interest shifts and item characteristics. We introduce novel evaluation metrics and user simulators to benchmark LLM-IPP against traditional methods. Our experiments demonstrate that LLM-IPP significantly enhances user acceptability and path coherence, outperforming existing approaches.

Problem

• Planning influence paths to expand user interests beyond historical preferences
• Addressing lack of target item inclusion and path coherence in recommendations
• Leveraging LLMs for coherent and effective proactive recommendation paths

Innovation

• Leverages LLMs for influence path planning
• Generates coherent paths with interest shifts
• Introduces novel metrics and user simulators