13 citations · 15 across the 4 of their papers we have counts for
4 papers
Momentum Calibration for Text Generation
Xingxing Zhang, Yiran Liu, Xun Wang +5
The input and output of most text generation tasks can be transformed to two sequences of tokens and they can be modeled using sequence-to-sequence learning modeling tools such as…
Does Debiasing Inevitably Degrade the Model Performance
Yiran Liu, Xiao Liu, Haotian Chen +1
Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performan…
Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust
Haotian Chen, Lingwei Zhang, Yiran Liu +2
Legal Judgment Prediction (LJP), aiming to predict a judgment based on fact descriptions according to rule of law, serves as legal assistance to mitigate the great work burden of l…
Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
Xiao Liu, Jiajie Zhang, Siting Li +2
What mechanisms causes GAN's entanglement? Although developing disentangled GAN has attracted sufficient attention, it is unclear how entanglement is originated by GAN transformati…