Papers by Zhihang Tan

1 papers
Surprise Calibration for Better In-Context Learning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for in-context learning apply fixed class priors across all inputs . existing methods rely on retraining and retrain models .
Approach: They propose a Bayesian-based method to capture the temporal dynamics of class priors . they identify "surprise" as an informative signal for class prior shift .
Outcome: The proposed method outperforms existing methods on a range of benchmark tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations