让AI实时理解用户目标，生成定制化工具和回答。
Just-In-Time Objectives: A General Approach for Specialized AI Interactions
- 通过观察用户行为自动推断即时目标，动态优化AI输出。
- 在实际任务中使LLM输出胜率提升至66%-86%。
- 适合需要个性化交互的科研、写作等场景使用者。
大型语言模型虽具备广泛功能，但缺乏明确目标时会返回通用结果。本文提出“即时目标”（Just-in-Time Objectives）机制，通过被动观测用户行为推断其当下目标，并实时优化模型以达成该目标。该方法构建了自动诱导目标的架构，通过生成与评估过程持续引导下游AI系统。例如，当目标为“澄清摘要的研究贡献”时，可自动生成批判草稿、预判同行反应或识别模糊术语的工具。在真实用户任务实验中，基于即时目标的输出在66%-86%的测试中优于普通LLM。亲测表明，该方法生成的工具具有个体独特性，且质量显著高于标准LLM对话工具。
原文摘要 · Abstract (English)
Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular objective, enables LLMs to produce specialized tools, interfaces, and responses. Our work introduces just-in-time objectives, which model a user's goals to specialize LLM systems on the fly. We contribute an architecture for automatically inducing such objectives by passively observing user behavior, then steering downstream AI systems through generation and evaluation against this objective. Inducing just-in-time objectives (e.g., "Clarify the abstract's research contribution") enables automatic generation of tools, e.g., those that critique a draft based on relevant HCI methodologies, anticipate related researchers' reactions, or surface ambiguous terminology. In a series of experiments on participants' own tasks, JIT objectives enable LLM outputs that achieve 66-86% win rates over typical LLMs. In-person use sessions confirm that JIT objectives produce specialized tools that are unique to each participant and are rated as significantly higher quality than a standard LLM chat tool.
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。