37 citations · 357 across the 52 of their papers we have counts for
83 papers
DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
Zhengfu He, Tianxiang Sun, Kuanning Wang +2
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training ob…
Efficient Adversarial Training with Robust Early-Bird Tickets
Zhiheng Xi, Rui Zheng, Tao Gui +2
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than tr…
Robust Lottery Tickets for Pre-trained Language Models
Rui Zheng, Rong Bao, Yuhao Zhou +6
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching acc…
Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts
Xiangyang Liu, Tianxiang Sun, Xuanjing Huang +1
Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the promp…
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
Tianxiang Sun, Junliang He, Xipeng Qiu +1
Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been com…
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
Songyang Gao, Shihan Dou, Qi Zhang +1
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models. The current mainstream solution is designing…