CAREER: Robust, Fair, and Culturally Aware Commonsense Reasoning in Natural Language

职业：用自然语言进行稳健、公平和具有文化意识的常识推理

• 批准号: 2339746
• 负责人: Rachel Rudinger
• 金额: $ 59.89万
• 依托单位: University of Maryland, College Park
• 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: 2024-05-01 至 2029-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2339746&HistoricalAwards=false
• 关键词: CAREER; Robust; Fair; Culturally; Aware

Recent advances in artificial intelligence have led to the proliferation of Large Language Models (LLMs). LLMs are models that cane be used for interactions with human users through written language; for example, a user inputs an instruction or question in English to the LLM-based program, and the LLM outputs a response in fluent English. With these linguistic capabilities, LLMs are being developed for use in applications that are both ubiquitous (e.g., internet search, customer support, writing tools) and high-stakes (e.g., mental health care, classroom education, assistive technology for people with disabilities). Despite their growing adoption, many fundamental properties of LLMs aren’t yet well understood, and pressing questions remain about when and whether LLMs can be entrusted with such important tasks. For example, when instructed to make simple predictions about every-day situations, like cooking a meal or riding in a vehicle, LLMs can make strange and surprising errors, exhibiting concerning lapses in basic common sense judgment and reasoning abilities. Additionally, these predictions made by LLMs can reflect social stereotypes and cultural assumptions which, at best, limit the usefulness of the technology for certain populations and, at worst, cause active harm. This project seeks to address unfairness and bias due to stereotyping and cultural context by proposing a generalized framework for defeasible commonsense inference in natural language in which a system compares two similar situations with respect to their support for a given inference. The proposed work aims at developing scientific methods to measure and improve the abilities of LLMs to (1) reason correctly about every-day situations, (2) do so in a manner that is fair and unprejudiced, and (3) adapt these reasoning abilities across specific cultural contexts. By measuring these fundamental capabilities of LLMs, we can better understand and mitigate the risks of applying this technology in high-stakes settings.The three phases of the project focus on the (1) robustness, (2) social fairness, and (3) cultural awareness dimensions of reasoning in LLMs. The project assumes a basic task formulation in which a situation description is provided to an LLM (e.g., “Someone drops a glass”), and the LLM must either evaluate a possible inference, or generate an inference from scratch (“The glass breaks”). In phase 1, methods will be developed to automatically manipulate situation descriptions in order to train and evaluate an LLM’s ability to make nuanced inferences, with the goal of learning to distinguish which factors influence a particular inference and which ones do not (e.g., when trying to predict if a dropped glass is going to break, the thickness of the glass matters but the color of the glass does not.) In phase 2, methods will be developed to automatically test whether LLMs make socially fair inferences, for example via name substitution tests, and to intervene when a proposed output is detected as unfair. In phase 3, survey participants from the U.S. and Ghana will answer multiple stages of questions about every-day situations; the collected data will be used to develop evaluation questions for a case study on the adaptability of LLMs across these two cultural settings. For each phase of the project, the resulting datasets, methods, and scientific findings will be made available to the public.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.

人工智能的最新进展导致了大语言模型（LLMS）的扩散。 LLMS是通过书面语言与人类用户互动的模型；例如，用户向基于LLM的程序输入以英语输入指令或问题，而LLM以流利的英语输出响应。借助这些语言能力，LLM正在开发用于无处不在的应用程序（例如互联网搜索，客户支持，写作工具）和高风险（例如，精神卫生保健，课堂教育，针对残疾人的辅助技术）。尽管采用了越来越多的采用，但LLM的许多基本属性尚未得到充分的理解，并且关于LLM何时以及是否可以执行此类重要任务的迫切问题。例如，当指示对每天情况（例如烹饪饭菜或骑车）做出简单的预测时，LLM会犯出奇怪而令人惊讶的错误，这是关于基本常识的判断和推理能力的失误。此外，LLMS做出的这些预测可以反映社会刻板印象和文化假设，最多只能限制该技术对某些人群的有用性，并且在最坏的情况下造成了主动伤害。该项目试图通过提出一个普遍的框架来解决自然语言的不可义的常识推论，以解决由于刻板印象和文化背景而引起的不公平和偏见，在这种框架中，系统将系统比较了两个相似情况就其支持给定推断进行比较。拟议的工作旨在开发科学方法来衡量和提高LLM的能力（1）（1）（1）对每天情况正确的原因，（2）以公平而毫无判断的方式进行，以及（3）在特定文化背景下调整这些推理能力。通过衡量LLM的这些基本能力，我们可以更好地理解和减轻在高风险环境中应用这项技术的风险。项目的三个阶段侧重于（1）鲁棒性，（2）社会公平，以及（3）LLMS中推理的文化意识维度。该项目假设一个基本的任务公式，其中将情况描述提供给LLM（例如“某人丢下玻璃”），LLM必须评估可能的推断，或者在第1阶段中生成一种方法，以自动操纵状况描述，以与训练的能力不同，以使llm的学习能力自动操纵状况描述，以划分llm的学习能力，而不是插入llm selliss的能力。 （例如，当试图预测掉落的玻璃是否会破裂时，玻璃的厚度很重要，但玻璃的颜色却没有。）在第2阶段中，将开发方法以自动测试LLMS是否可以通过名称替代测试进行社会上的公平推断，并在检测到提出的输出时进行干预。在第3阶段，来自美国和加纳的调查参与者将回答有关每天情况的多个问题的阶段；收集的数据将用于为有关LLM在这两种文化环境中的适应性的案例研究制定评估问题。对于项目的每个阶段，最终的数据集，方法和科学发现将提供给公众。该奖项反映了NSF的法定任务，并使用基金会的知识分子优点和更广泛的影响审查标准，通过评估诚实地认为支持了支持。