High-Dimension Human Value Representation in Large Language Models

2024/04/11 by Samuel Cahyawijaya, Cahyawijaya, Samuel, Delong Chen +13 · 5 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2404.07900

openalex publication_date 2024/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The widespread application of LLMs across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, there is an urgent need to understand the scope and nature of human values injected into these LLMs before their deployment and adoption. We propose UniVaR, a high-dimensional neural representation of symbolic human value distributions in LLMs, orthogonal to model architecture and training data. This is a continuous and scalable representation, self-supervised from the value-relevant output of 8 LLMs and evaluated on 15 open-source and commercial LLMs. Through UniVaR, we visualize and explore how LLMs prioritize different values in 25 languages and cultures, shedding light on complex interplay between human values and language modeling.

Cited by

• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?
• Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
• Embodied AI Agents: Modeling the World
• The Multilingual Divide and Its Impact on Global AI Safety
• AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

Related

• Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches
• Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
• Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values
• ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models
• Fine-tuning vs Prompting, Can Language Models Understand Human Values?