How Inclusively do LMs Perceive Social and Moral Norms?

TL;DR

This study evaluates how well language models perceive social and moral norms across different demographic groups, revealing disparities that highlight the need for more inclusive AI systems.

Contribution

Introduces the ADA-Met metric and compares 11 LMs' norm perceptions with human responses across demographics, exposing gaps in inclusivity.

Findings

Younger and higher-income groups' responses align more closely with LMs.

Significant disparities in LM perceptions across demographic groups.

Highlights the need for more inclusive language model training.

Abstract

This paper discusses and contains offensive content. Language models (LMs) are used in decision-making systems and as interactive assistants. However, how well do these models making judgements align with the diversity of human values, particularly regarding social and moral norms? In this work, we investigate how inclusively LMs perceive norms across demographic groups (e.g., gender, age, and income). We prompt 11 LMs on rules-of-thumb (RoTs) and compare their outputs with the existing responses of 100 human annotators. We introduce the Absolute Distance Alignment Metric (ADA-Met) to quantify alignment on ordinal questions. We find notable disparities in LM responses, with younger, higher-income groups showing closer alignment, raising concerns about the representation of marginalized perspectives. Our findings highlight the importance of further efforts to make LMs more inclusive of diverse human values. The code and prompts are available on GitHub under the CC BY-NC 4.0 license.