LLMs deviate from human moral preferences in kidney allocation scenarios and rarely express indecision, though low-rank fine-tuning with few examples can improve both consistency and uncertainty calibration.
Assessing moral decision making in large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CY 2verdicts
UNVERDICTED 2representative citing papers
A policy-based RL agent plays a 20 questions game to recommend optimal cybersecurity education and explain the decision by eliciting the minimal set of evidential facts needed to justify defensive actions.
citing papers explorer
-
Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
LLMs deviate from human moral preferences in kidney allocation scenarios and rarely express indecision, though low-rank fine-tuning with few examples can improve both consistency and uncertainty calibration.
-
Learning-to-Explain through 20Q Gaming: An Explainable Recommender for Cybersecurity Education
A policy-based RL agent plays a 20 questions game to recommend optimal cybersecurity education and explain the decision by eliciting the minimal set of evidential facts needed to justify defensive actions.