作者位次 #2/5ACL 2026Poster· Natural Language Processing
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
Lillian Sun · Martin Pawelczyk · Zhenting Qi · Aounon Kumar · Himabindu Lakkaraju
摘要
As large language models continue to advance, ensuring their trustworthiness is critical. However, inaccessible real-world ground truth labels pose a significant challenge in high-stakes domains. Recent studies have highlighted weak-to-strong generalization, where a strong model trained only on a...