会求助的机器人：面向大语言模型规划器的不确定性对齐
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
AI总结：
本文提出KnowNo框架，利用共形预测对齐大语言模型规划器的不确定性，使其在复杂多步任务中自知不足并适时求助，实验证明其优于基线，提升效率与自主性。
摘要：
大语言模型（LLMs）展现出广泛的有前景的能力——从逐步规划到常识推理——这些能力可能为机器人提供实用价值，但仍容易产生自信的幻觉预测。在这项工作中，我们提出了KnowNo，这是一个用于测量和对齐基于LLM的规划器不确定性的框架，使得它们能够知道自己不知道的内容，并在需要时寻求帮助。KnowNo基于共形预测理论，在复杂的多步规划环境中，在最小化人类帮助的同时，为任务完成提供统计保证。在涉及不同歧义模式（例如，从空间到数值不确定性，从人类偏好到Winograd模式）的任务的各种模拟和真实机器人设置中进行的实验表明，与现代基线（可能涉及集成或广泛的提示调整）相比，KnowNo在提高效率和自主性方面表现更优，同时提供正式保证。KnowNo可以直接与LLM一起使用，无需模型微调，并提出了一种有前景的轻量级不确定性建模方法，可以补充并随着基础模型不断增长的能力而扩展。网站：https://robot-help.github.io
英文摘要：
Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions. In this work, we present KnowNo, which is a framework for measuring and aligning the uncertainty of LLM-based planners such that they know when they don't know and ask for help when needed. KnowNo builds on the theory of conformal prediction to provide statistical guarantees on task completion while minimizing human help in complex multi-step planning settings. Experiments across a variety of simulated and real robot setups that involve tasks with different modes of ambiguity (e.g., from spatial to numeric uncertainties, from human preferences to Winograd schemas) show that KnowNo performs favorably over modern baselines (which may involve ensembles or extensive prompt tuning) in terms of improving efficiency and autonomy, while providing formal assurances. KnowNo can be used with LLMs out of the box without model-finetuning, and suggests a promising lightweight approach to modeling uncertainty that can complement and scale with the growing capabilities of foundation models. Website: https://robot-help.github.io
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。
