一作ACL 2026Poster· Natural Language Processing
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
Hanwen Shen · Ting Ying · Jiajie Lu · Shanshan Wang
摘要
Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a distribution shift, degrading static model performance. To e...