作者位次 #4/5ACL 2026Poster· Natural Language Processing
Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q -Sorts
Jingting Zheng · Yuqi Ren · Linhao Yu · Yongqi Leng · Deyi Xiong
摘要
Large Language Models (LLMs) are increasingly deployed in contexts requiring complex moral reasoning and value trade-offs. However, existing evaluations typically rely on item-level behavioral metrics, which fail to capture how models structurally prioritize competing values as a cohesive system....