CAREER: Controllable generation for instruction-following language models

职业：指令跟随语言模型的可控生成

• 批准号: 2338866
• 负责人: Tatsunori Hashimoto
• 金额: $ 53.13万
• 依托单位: Stanford University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-04-15 至 2029-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2338866&HistoricalAwards=false
• 关键词: CAREER; Controllable; generation; instruction; following

Instruction-following language models like ChatGPT are beginning to see widespread development, and the ability to understand these systems and control them is critically important to make sure that they benefit society. Despite the success of these language models in generating fluent and convincing-looking outputs, there has been a growing body of work indicating that these systems can generate outputs that are undesirable to users, model creators, and even society at large. This gap between the ability to create models that imitate humans and the inability to have them fulfill specific desiderata (e.g. refuse to generate incorrect information) shows a major deficiency in the ability to precisely control these systems. This project aims to build principled, transparent, and precise methods for controlling language models.To achieve these goals, this project views controllable generation as a viable long-term path to creating instruction-following language models that precisely follow our design goals. Controllable generation offers several benefits. First, it defines a precise statistical modeling problem on which it is possible to build principled methods and rigorous evaluations. Second, it separates the control target from the task, improving transparency by allowing users to see exactly what is being optimized by the model designers. Third, it enables much more precise controls via inference-time methods such as rejection sampling, which strictly enforces the control as a constraint. While controllable generation has major long-term benefits for language models, there also remain significant open problems that must be resolved first, including the difficulty of performing discrete search, the need for specialized training, and the lack of realistic benchmarks of control tasks in the wild. We will address these challenges through a combination of new models (such as diffusion-based models), zero-shot and decoder-based control methods, and a broad benchmark of in-the-wild control behaviors.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.

像ChatGPT这样的遵循指令的语言模型开始广泛发展，理解这些系统并控制它们的能力对于确保它们造福社会至关重要。尽管这些语言模型在生成流畅和令人信服的输出方面取得了成功，但越来越多的工作表明，这些系统可以生成用户，模型创建者甚至整个社会都不希望的输出。创建模仿人类的模型的能力与无法让它们满足特定需求（例如拒绝生成不正确的信息）之间的这种差距表明，精确控制这些系统的能力存在重大缺陷。该项目旨在建立有原则的、透明的和精确的方法来控制语言模型。为了实现这些目标，该项目将可控生成视为一种可行的长期途径，以创建精确遵循我们设计目标的遵循规则的语言模型。可控发电有几个好处。首先，它定义了一个精确的统计建模问题，在这个问题上可以建立原则性的方法和严格的评估。其次，它将控制目标与任务分离，通过允许用户确切地看到模型设计者正在优化的内容来提高透明度。第三，它通过推理时间方法（如拒绝采样）实现更精确的控制，严格执行控制作为约束。虽然可控生成对语言模型有重大的长期好处，但也存在必须首先解决的重大开放问题，包括执行离散搜索的困难，需要专门的培训，以及缺乏现实的控制任务基准。我们将通过结合新模型（如基于扩散的模型）、基于零发射和解码器的控制方法以及野外控制行为的广泛基准来应对这些挑战。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。