Author

Yan-Li Chen

h-index 8 View on Semantic Scholar

We have 1 of 52 papers

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.

Preprint Sep 2026

Beyond QA Matching: Perturbation-Response Fingerprinting via Probability Distributions for Large Language Models

BReF is introduced, a training-free fingerprint that compares how probability distributions over four answer-option labels A/B/C/D move under controlled textual perturbations, and shows that strong pooled separation does not guarantee correct parent ranking among closely related checkpoints.

Ji-Chao Zeng, Yan-Li Chen, Han-Zhou Wu · 0 citations