Author

Yu-Chung Hsiao

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models

It is shown that the standard advice to prefer log-probabilities no longer holds on post-2025 models, where verbalized confidence is the better signal, and recommended broader use of soft scoring in LLM-as-a-Judge is recommended.

Yu-Chung Hsiao · 1 citation