让大模型更懂用户偏好，智能调用工具完成个性化任务
TAPS: Tool-Augmented Personalisation via Structured Tagging
- 用结构化标签和不确定度检测器提升工具调用的个性化能力
- 在NLSI任务上超越开源模型现有水平，实现新最佳性能
- 适合需要个性化交互的对话系统开发者参考
近期工具增强型大语言模型已能与外部工具交互，提升复杂任务执行能力。然而，现有方法忽视了个性化在引导工具使用中的作用。本文研究如何将用户偏好有效融入目标导向对话代理中。通过大量分析，我们识别出大模型在个性化工具使用上的关键缺陷。为此，提出TAPS：一种利用结构化标签工具和基于不确定性的工具检测器来增强个性化工具使用的方案。TAPS显著提升了大模型融入用户偏好的能力，在NLSI任务上达到开源模型的新最优表现。
原文摘要 · Abstract (English)
Recent advancements in tool-augmented large language models have enabled them to interact with external tools, enhancing their ability to perform complex user tasks. However, existing approaches overlook the role of personalisation in guiding tool use. This work investigates how user preferences can be effectively integrated into goal-oriented dialogue agents. Through extensive analysis, we identify key weaknesses in the ability of LLMs to personalise tool use. To this end, we introduce TAPS, a novel solution that enhances personalised tool use by leveraging a structured tagging tool and an uncertainty-based tool detector. TAPS significantly improves the ability of LLMs to incorporate user preferences, achieving the new state-of-the-art for open source models on the NLSI task.
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。