What's the most important value? INVP: INvestigating the Value Priorities of LLMs through Decision-making in Social Scenarios
Abstract: As large language models (LLMs) demonstrate impressive performance in various tasks and are increasingly integrated into the decision-making process, ensuring they align with human values has become crucial. This paper highlights that value priorities(the relative importance of different value) play a pivotal character in the decision-making process. To explore the value priorities in LLMs, this paper introduces INVP, a framework for INvestigating Value Priorities through decision-making in social scenarios. The framework encompasses social scenarios including binary decision-making, covering both individual and collective decision-making contexts, and is based on Schwartz's value theory for constructing value priorities. Based on this framework, we construct a dataset, which contains a total of 1613 scenarios and 3226 decisions across 283 topics. We evaluated seven popular LLMs and the experimental results reveal commonalities in the value priorities across different LLMs, such as an emphasis on Universalism and Benevolence, while Power and Hedonism are typically given lower priority.
This study offers new perspectives on understanding and improving the moral and value alignment of LLMs in making complex social decisions.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: LLM evaluation, value priority, decision-maiking
Contribution Types: Model analysis & interpretability, Data resources
Languages Studied: chinese
Submission Number: 3296
Loading