RI: Small: Extracting Knowledge from Language Models for Decision Making

RI：小型：从语言模型中提取知识以进行决策

• 批准号: 2246811
• 负责人: Sergey Levine
• 金额: $ 60万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-15 至 2026-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2246811&HistoricalAwards=false
• 关键词: RI; Small; Extracting; Knowledge; Language

This project aims to integrate semantic knowledge from large language models into automated decision-making and control systems while retaining reliability and robustness. The main principle of the proposed approach is to use language models to generate proposals and guidance, but still make the final decision or plan based on principled and robust planning and control methods, such that the language models are used when their semantic predictions are useful but not relied upon to always yield the correct answer. Large language models, such as ChatGPT, have garnered considerable attention in recent years due to their ability to respond to complex user queries and fulfill elaborate requests, such as writing code, composing stories, or providing educational explanations. Because of this, there is considerable interest in using them directly as decision-making systems (for example, if a language model can give “how to” instructions for repairing a car, perhaps it can also issue commands to a robot that actually repairs a car). However, there are also numerous concerns that such models might be too unreliable or too prone to generate false predictions to be useful as decision-making systems on their own. Therefore, this project aims to integrate these models into principled methods for planning and control to leverage the semantic knowledge in these models while providing a degree of robustness. This research has significant ramifications for automated decision-making systems that need to interact with complex real-world environments, where both semantic reasoning and intelligent planning are important. This includes robotic systems, including autonomous vehicles and service robots, intelligent assistants, decision support systems, and a range of automation technologies.The technical approach in this project will be based around a probabilistic formulation that ties together the ungrounded semantic predictions from language models with grounded but non-semantic predictions from learned dynamics models. In this way, probabilistic inference machinery can be used to derive algorithms that make decisions that have a high likelihood of being semantically good according to the language model and a high likelihood of being physically (dynamically) optimal according to the learned dynamics model. In practice, this principle can be instantiated in the context of both model-based and model-free reinforcement-learning systems, learned prediction systems, and planning algorithms (by formulating planning as inference). The project will explore applications of this concept to prediction, planning and control, and exploration in reinforcement learning.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目旨在将大型模型的语义整合到自动化的决策和控制系统中，同时保留了鲁棒性和鲁棒性。有原则性和健壮的计划和控制方法，当时使用这种语言模型，但由于其能够组合用户查询和履行诸如编写代码，编写故事L的能力，因此无法始终产生正确的答案。因此。因此汽车）众多的担忧，即这种模型可能会引起虚假的预测，因此可以在这些模型中计划和控制语义知识。制造需要复杂的现实环境的系统很重要。从学习动力学模型中的语言模型中进行语义预测，可以将NCE机械的模型从原则上可以根据学习的动力学模型来得出算法。在基于模型的和无模型的增强系统，学习的预测系统和计划算法的背景下进行实例化（通过将计划作为推理提出）。奖项使用Toundation的Revader对W标准的Revader take Recteriation进行了Suthy评估的NSF'Sf'Stututory。