Abstract: Existing research assesses LLMs’ values by analyzing their stated inclinations, overlooking potential discrepancies between stated values
and actions—termed the “Value-Action Gap.” This study introduces ValueActionLens, a framework to evaluate the alignment between
LLMs’ stated values and their value-informed actions. The framework includes a dataset of 14.8k value-informed actions across 12 cultures
and 11 social topics, along with two tasks measuring alignment through three metrics. Experiments show substantial misalignment between
LLM-generated value statements and their actions, with significant variations across scenarios and models. Misalignments reveal potential
harms, highlighting risks in relying solely on stated values to predict behavior. The findings stress the need for context-aware evaluations of LLM values and the value-action gaps.
Paper Type: Long
Research Area: Special Theme (conference specific)
Research Area Keywords: Safety and Alignment in LLMs, Value Alignment
Contribution Types: Model analysis & interpretability, Data resources
Languages Studied: English
Submission Number: 2141
Loading