用大模型生成对话摘要，让推荐更贴近真实聊天
Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization
- 用LLM从对话中提取显性和隐性偏好
- 通过直接偏好优化提升推荐信息丰富度
- 适合想改进对话推荐自然性的研究者
对话推荐系统（CRS）旨在通过自然对话获取用户偏好并提供合适推荐。然而，现有系统常在简短会话中快速推荐，偏离真实人类交互。本文利用大语言模型（LLMs）从对话历史和物品描述中生成对话摘要与推荐信息，从而提取显性陈述及上下文推断的隐性偏好。提出一种基于直接偏好优化（DPO）的方法，确保对话摘要和推荐内容富含关键信息。在两个公开数据集上的实验验证了该方法在促进更自然、真实的对话推荐过程中的有效性。代码已公开于：https://github.com/UEC-InabaLab/Refining-LLM-Text
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。