一作ACL 2026Poster· Natural Language Processing
Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation
Huizi Cui · Huan Ma · Qilin Wang · Yuhang Gao · Changqing Zhang
摘要
Large language models (LLMs) have progressed rapidly in complex reasoning and question answering, yet LLM hallucination remains a central bottleneck that hinders practical deployment, especially for commercial black-box LLMs accessible only via APIs. Existing uncertainty quantification methods ty...