High-Dimension Human Value Representation in Large Language Models
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.
Code (1)
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
High-Dimensional Discrete Bayesian Optimization with Self-Supervised Representation Learning for Data-Efficient Materials Exploration
A material exploration model based on high-dimensional discrete Bayesian optimization is introduced. Features were extracted from a large-scale database of ab-initio calculations by self-supervised representation learnin…
Bayesian OptimizationRepresentation LearningThe high dimensional psychological profile and cultural bias of ChatGPT
Given the rapid advancement of large-scale language models, artificial intelligence (AI) models, like ChatGPT, are playing an increasingly prominent role in human society. However, to ensure that artificial intelligence …
Decision MakingNumber Representations in LLMs: A Computational Parallel to Human Perception
Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones. This cognitive bias, supported by neuroscience and behavioral st…
Dimensionality ReductionSelf-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion
We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are lea…
Activity RecognitionHuman Activity RecognitionSelf-Supervised LearningNeurosymbolic Value-Inspired AI (Why, What, and How)
The rapid progression of Artificial Intelligence (AI) systems, facilitated by the advent of Large Language Models (LLMs), has resulted in their widespread application to provide human assistance across diverse industries…
Autonomous DrivingDecision Making