# Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization

## TL;DR

This paper enhances conversational recommender systems by using large language models to generate detailed dialogue summaries and item recommendations, employing direct preference optimization to improve realism and effectiveness in dialogue-based recommendations.

## Contribution

It introduces a novel method combining LLM-generated dialogue summaries with direct preference optimization to produce more natural and effective conversational recommendations.

## Key findings

- Improved recommendation relevance in dialogue settings
- Enhanced naturalness of conversational interactions
- Validated on two public datasets

## Abstract

Conversational Recommender Systems (CRSs) aim to elicit user preferences via natural dialogue to provide suitable item recommendations. However, current CRSs often deviate from realistic human interactions by rapidly recommending items in brief sessions. This work addresses this gap by leveraging Large Language Models (LLMs) to generate dialogue summaries from dialogue history and item recommendation information from item description. This approach enables the extraction of both explicit user statements and implicit preferences inferred from the dialogue context. We introduce a method using Direct Preference Optimization (DPO) to ensure dialogue summary and item recommendation information are rich in information crucial for effective recommendations. Experiments on two public datasets validate our method's effectiveness in fostering more natural and realistic conversational recommendation processes. Our implementation is publicly available at: https://github.com/UEC-InabaLab/Refining-LLM-Text