2 papers
cs.CL2025
McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models
Tian Lan, Xiangdong Su, Xu Liu +4
As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to miti…
cs.CL2025
RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models
Fujun Zhang, Xiaoying Fan, XiangDong Su +1
Fine-tuning pre-trained language models (PLMs) has become a dominant paradigm in applying PLMs to downstream tasks. However, with limited fine-tuning, PLMs still struggle with the…