DiscoverLLM：从执行意图到发现意图
DiscoverLLM: From Executing Intents to Discovering Them
AI总结：
DiscoverLLM通过引入新的用户模拟器，帮助用户形成和发现意图，提升任务性能并减少对话长度。
摘要：
为处理模糊和开放性请求，大型语言模型（LLMs）越来越多地被训练以与用户互动，以揭示尚未表达的意图（例如，询问澄清问题）。然而，用户往往模糊，因为他们尚未形成意图：他们必须观察和探索结果以发现想要什么。简单地问“你想要什么样的语气？”在用户自己不知道时会失败。我们引入了DiscoverLLM，一种新颖且可推广的框架，训练LLMs帮助用户形成和发现意图。我们的方法核心是一个新的用户模拟器，通过意图的分层模型来建模认知状态，这些意图随着模型揭示相关选项而逐步具体化——具体化的程度作为奖励信号，模型可以被训练以优化。最终模型学会通过适应性地发散（即探索选项）来与用户合作，当意图不明确时，以及通过收敛（即细化和实施）来优化意图。在创意写作、技术写作和SVG绘图等提出的交互基准中，DiscoverLLM实现了超过10%的任务性能提升，同时将对话长度减少多达40%。在75名人类参与者的用户研究中，DiscoverLLM在满意度和效率方面优于基线。
英文摘要：
To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they have not yet expressed (e.g., ask clarification questions). However, users are often ambiguous because they have not yet formed their intents: they must observe and explore outcomes to discover what they want. Simply asking "what kind of tone do you want?" fails when users themselves do not know. We introduce DiscoverLLM, a novel and generalizable framework that trains LLMs to help users form and discover their intents. Central to our approach is a novel user simulator that models cognitive state with a hierarchy of intents that progressively concretize as the model surfaces relevant options -- where the degree of concretization serves as a reward signal that models can be trained to optimize. Resulting models learn to collaborate with users by adaptively diverging (i.e., explore options) when intents are unclear, and converging (i.e., refine and implement) when intents concretize. Across proposed interactive benchmarks in creative writing, technical writing, and SVG drawing, DiscoverLLM achieves over 10% higher task performance while reducing conversation length by up to 40%. In a user study with 75 human participants, DiscoverLLM improved conversation satisfaction and efficiency compared to baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
