Leveraging LLM Reasoning Enhances Personalized Recommender Systems

TL;DR

This paper investigates how leveraging Large Language Model reasoning, through Chain-of-Thought prompting and a new evaluation framework, can enhance personalized recommender systems by improving reasoning quality and alignment with human judgment.

Contribution

It introduces RecSAVER, an automatic evaluation framework for LLM reasoning in RecSys, and demonstrates how reasoning improves recommendation quality in zero-shot and finetuning settings.

Findings

LLM reasoning improves recommendation personalization.

RecSAVER aligns with human judgment on reasoning quality.

Reasoning enhances RecSys performance in various settings.

Abstract

Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.