.png){kind=icon}
.png){kind=icon}
Return
Would ChatGPT Help Me Eat My Dead Dog? Probing Moral Judgment and Moral Action in Large Language Models
.png){kind=icon}
OA
AI
DOI：10.1016/j.chbr.2026.101063.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Large language models reproduce key features of human intuitive morality in harmless but emotionally provocative scenarios • Moral wrongfulness judgments in models rely on affect based botherness rather than perceived harm • Models express moral condemnation of taboo actions yet show greater permissiveness than humans • When placed in an agentic context, models often assist with actions they judge to be morally wrong, revealing a judgment action gap
Keywords:
Moral judgment
Moral action
Large language models
Ethical reasoning
Judgment-action gap
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
5.8
Papers:
424
Citations:
0