StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models
This work addresses the issue of harmful biases in AI for researchers and practitioners, though it is incremental as it applies an existing psychological theory to LLMs without introducing a new mitigation method.
The authors tackled the problem of quantifying stereotypes in large language models by proposing StereoMap, a framework based on the Stereotype Content Model, which maps perceptions of social groups along warmth and competence dimensions and analyzes reasoning, finding that LLMs exhibit diverse perceptions and awareness of social disparities.
Large Language Models (LLMs) have been observed to encode and perpetuate harmful associations present in the training data. We propose a theoretically grounded framework called StereoMap to gain insights into their perceptions of how demographic groups have been viewed by society. The framework is grounded in the Stereotype Content Model (SCM); a well-established theory from psychology. According to SCM, stereotypes are not all alike. Instead, the dimensions of Warmth and Competence serve as the factors that delineate the nature of stereotypes. Based on the SCM theory, StereoMap maps LLMs' perceptions of social groups (defined by socio-demographic features) using the dimensions of Warmth and Competence. Furthermore, the framework enables the investigation of keywords and verbalizations of reasoning of LLMs' judgments to uncover underlying factors influencing their perceptions. Our results show that LLMs exhibit a diverse range of perceptions towards these groups, characterized by mixed evaluations along the dimensions of Warmth and Competence. Furthermore, analyzing the reasonings of LLMs, our findings indicate that LLMs demonstrate an awareness of social disparities, often stating statistical data and research findings to support their reasoning. This study contributes to the understanding of how LLMs perceive and represent social groups, shedding light on their potential biases and the perpetuation of harmful associations.