作者位次 #2/3ACL 2026Poster· Natural Language Processing
Inertia in Moral and Value Judgments of Large Language Models
Bruce W. Lee · Yeongheon Lee · Hyunsoo Cho
摘要
Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs.A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses, similar to how responses vary across human individuals.Against...