The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models

TL;DR

This paper reviews methods for evaluating attitudes, opinions, and values in large language models, highlighting challenges, potential, and interdisciplinary approaches to better understand and align LLMs with human-like traits.

Contribution

It provides a comprehensive overview of current evaluation methods for AOVs in LLMs and discusses challenges and practical insights for future research.

Findings

Evaluation methods vary and can produce different results.

Understanding AOVs is crucial for human-AI alignment.

Interdisciplinary collaboration enhances evaluation strategies.

Abstract

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.