作者位次 #4/4ACL 2026Findings· Findings of ACL
How Value Induction Reshapes LLM Behavior
Arnav Arora · Natalie Schluter · Katherine Metcalf · Maartje Ter Hoeve
摘要
Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to increase utility, ensure safety, and improve the user experien...