用扩散模型思路训练LLM问问题，更好挖掘用户偏好。
Asking Clarifying Questions for Preference Elicitation With Large Language Models
- 借鉴扩散模型思想，分步生成并修正提问序列。
- 在无历史数据场景下，偏好获取准确率提升显著。
- 适合需要深度交互的个性化推荐系统使用。
大型语言模型（LLMs）使推荐系统可通过开放式对话界面与用户互动。为个性化响应，需在用户历史有限时有效获取其偏好。一种方法是提出澄清性问题以获取更多信息。然而，在不同领域生成有效的连续澄清问题仍具挑战。为此，我们提出一种新方法，训练LLMs生成能揭示用户偏好的序列化问题。该方法受扩散模型启发，采用两阶段流程：前向过程从用户档案出发，逐步生成澄清问题并移除回答，相当于对用户档案添加‘噪声’；反向过程则训练模型学习通过提问来‘去噪’，还原真实偏好。实验表明，该方法显著提升了LLM生成引导式问题的能力，有效促进了用户偏好的获取。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have made it possible for recommendation systems to interact with users in open-ended conversational interfaces. In order to personalize LLM responses, it is crucial to elicit user preferences, especially when there is limited user history. One way to get more information is to present clarifying questions to the user. However, generating effective sequential clarifying questions across various domains remains a challenge. To address this, we introduce a novel approach for training LLMs to ask sequential questions that reveal user preferences. Our method follows a two-stage process inspired by diffusion models. Starting from a user profile, the forward process generates clarifying questions to obtain answers and then removes those answers step by step, serving as a way to add ``noise'' to the user profile. The reverse process involves training a model to ``denoise'' the user profile by learning to ask effective clarifying questions. Our results show that our method significantly improves the LLM's proficiency in asking funnel questions and eliciting user preferences effectively.
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。