Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values

TL;DR

This paper introduces the Value Compass Benchmarks, a comprehensive platform for evaluating LLMs' values by clarifying underlying motivations, adapting to evolving models, and accounting for cultural value differences.

Contribution

It presents a novel evaluation framework with modules for value clarification, adaptive testing, and pluralistic value measurement, addressing limitations of existing benchmarks.

Findings

Provides a holistic view of LLMs' underlying values.

Develops an adaptive evaluation framework for evolving LLMs.

Introduces a metric for measuring value alignment considering cultural pluralism.

Abstract

As Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative for their responsible development and customized applications. However, there still lack evaluations of LLMs values that fulfill three desirable goals. (1) Value Clarification: We expect to clarify the underlying values of LLMs precisely and comprehensively, while current evaluations focus narrowly on safety risks such as bias and toxicity. (2) Evaluation Validity: Existing static, open-source benchmarks are prone to data contamination and quickly become obsolete as LLMs evolve. Additionally, these discriminative evaluations uncover LLMs' knowledge about values, rather than valid assessments of LLMs' behavioral conformity to values. (3) Value Pluralism: The pluralistic nature of human values across individuals and cultures is largely ignored in measuring LLMs value alignment. To address these challenges, we presents the Value Compass Benchmarks, with three correspondingly designed modules. It (i) grounds the evaluation on motivationally distinct \textit{basic values to clarify LLMs' underlying values from a holistic view; (ii) applies a \textit{generative evolving evaluation framework with adaptive test items for evolving LLMs and direct value recognition from behaviors in realistic scenarios; (iii) propose a metric that quantifies LLMs alignment with a specific value as a weighted sum over multiple dimensions, with weights determined by pluralistic values.