Assessing LLMs for Moral Value Pluralism

TL;DR

This paper develops a method using NLP to assess and quantify the implicit moral and cultural values in LLM outputs, revealing biases and misalignments with diverse demographics based on social science surveys.

Contribution

It introduces the Recognizing Value Resonance (RVR) model to evaluate implicit moral values in LLMs, enabling quantitative analysis of value alignment across cultures and demographics.

Findings

LLMs show Western-centric value biases.

They overestimate conservatism in non-Western countries.

They misrepresent gender and age-related values.

Abstract

The fields of AI current lacks methods to quantitatively assess and potentially alter the moral values inherent in the output of large language models (LLMs). However, decades of social science research has developed and refined widely-accepted moral value surveys, such as the World Values Survey (WVS), eliciting value judgments from direct questions in various geographies. We have turned those questions into value statements and use NLP to compute to how well popular LLMs are aligned with moral values for various demographics and cultures. While the WVS is accepted as an explicit assessment of values, we lack methods for assessing implicit moral and cultural values in media, e.g., encountered in social media, political rhetoric, narratives, and generated by AI systems such as LLMs that are increasingly present in our daily lives. As we consume online content and utilize LLM outputs, we might ask, which moral values are being implicitly promoted or undercut, or -- in the case of LLMs -- if they are intending to represent a cultural identity, are they doing so consistently? In this paper we utilize a Recognizing Value Resonance (RVR) NLP model to identify WVS values that resonate and conflict with a given passage of output text. We apply RVR to the text generated by LLMs to characterize implicit moral values, allowing us to quantify the moral/cultural distance between LLMs and various demographics that have been surveyed using the WVS. In line with other work we find that LLMs exhibit several Western-centric value biases; they overestimate how conservative people in non-Western countries are, they are less accurate in representing gender for non-Western countries, and portray older populations as having more traditional values. Our results highlight value misalignment and age groups, and a need for social science informed technological solutions addressing value plurality in LLMs.