HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

Benjamin Sturgeon, Daniel Samuelson, Jacob Haimes, Jacy Reese Anthis

Keywords: evaluations, human agency, human-computer interaction, large language models, AI assistants

TL;DR: We develop an adaptive and scalable framework for evaluating how LLMs support or reduce human agency, operationalized in six dimensions.

Abstract: As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems already steer human decision-making, such as social media feed algorithms that lead people to unintentionally and absent-mindedly scroll through engagement-optimized content. In this paper, we develop the idea of $\textit{human agency}$ by integrating philosophical and scientific theories of agency with AI-assisted evaluation methods: using large language models (LLMs) to simulate and validate user queries and to evaluate AI responses. We develop $\texttt{HumanAgencyBench}$ (HAB), a scalable and adaptive benchmark with six dimensions of human agency based on typical AI use cases. HAB measures the tendency of an AI assistant or agent to Ask Clarifying Questions, Avoid Value Manipulation, Correct Misinformation, Defer Important Decisions, Encourage Learning, and Maintain Social Boundaries. We find low-to-moderate agency support in contemporary LLM-based assistants and substantial variation across system developers and dimensions. For example, while Anthropic LLMs most support human agency overall, they are the least supportive LLMs in terms of Avoid Value Manipulation. Agency support does not appear to consistently result from increasing LLM capabilities or instruction-following behavior (e.g., RLHF), and we encourage a shift towards more robust safety and alignment targets.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 13339