The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
It addresses the lack of clarity in evaluating AOVs for researchers and practitioners in AI and social sciences, but is incremental as it surveys existing work rather than introducing new methods.
This paper tackles the problem of evaluating attitudes, opinions, and values (AOVs) in large language models, which is opaque and yields inconsistent results across methods, by providing a comprehensive overview and survey of recent works to address challenges in model understanding, human-AI alignment, and social science applications.
Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.