62 citations · 119 across the 26 of their papers we have counts for
4 papers · 1 filter
When Linguistic and Internal Confidence Diverge in Large Language Models
Hefan Zhang, Bingquan Zhang, Ming Cheng +3
Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study…
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation
Yahan Zheng, John Guerrerio, Soroush Vosoughi +1
Preprocessing-based methods for stereotype mitigation, such as pre-/post-training on debiased corpora, are widely used in NLP. While these approaches reduce measurable stereotypes…
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Weicheng Ma, John Guerrerio, Soroush Vosoughi
Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual…
Detecting and Enhancing Intellectual Humility in Online Political Discourse
Samantha D'Alonzo, Rachel Chen, Weidong Zhang +7
Intellectual humility (IH)-a recognition of one's own intellectual limitations-can reduce polarization and foster more understanding across lines of difference. Yet little work exp…