Leveraging LLMs for Influence Path Planning in Proactive Recommendation

TL;DR

This paper introduces LLM-IPP, a novel method leveraging large language models to improve influence path planning in proactive recommender systems, addressing coherence and target inclusion issues.

Contribution

It proposes an LLM-based influence path planning approach that enhances coherence and target inclusion in proactive recommendations, with new evaluation metrics and benchmarks.

Findings

LLM-IPP outperforms traditional methods in influence path coherence.

Enhanced user acceptability demonstrated through experiments.

Novel metrics and simulators for influence path evaluation.

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.