寻求帮助的机器人：大型语言模型规划者的不确定性对齐

摘要

大型语言模型（LLMs）展示了广泛的有前途的能力，从逐步规划到常识推理，这些能力可能为机器人提供帮助，但仍然容易出现自信地产生幻觉的预测。在这项工作中，我们提出了KnowNo，这是一个用于衡量和调整基于LLM的规划器不确定性的框架，使它们知道自己不知道并在需要时寻求帮助。KnowNo基于符合预测理论，提供任务完成的统计保证，同时在复杂的多步规划设置中最大限度地减少人类帮助。在涉及具有不同模糊模式的任务的各种模拟和真实机器人设置上进行的实验（例如，从空间到数字不确定性，从人类偏好到Winograd模式）表明，KnowNo在提高效率和自主性方面优于现代基线（可能涉及集成或广泛提示调整），同时提供正式保证。KnowNo可以直接与LLMs一起使用，无需模型微调，并提出了一种有前途的轻量级建模不确定性方法，可以补充并随着基础模型日益增强的能力而扩展。网站：https://robot-help.github.io

English

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

寻求帮助的机器人：大型语言模型规划者的不确定性对齐

Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners

摘要

Support