20 citations · 75 across the 44 of their papers we have counts for
7 papers · 1 filter
Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification
Ruixuan Tang, Hanjie Chen, Yangfeng Ji
Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model. This raises the interest and concern in the stability of…
KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales
Aaron Chan, Zhiyuan Zeng, Wyatt Lake +3
Language models (LMs) have yielded impressive results on many language reasoning tasks, but their unexpected errors raise doubts about their reasoning abilities. In light of this,…
REV: Information-Theoretic Evaluation of Free-Text Rationales
Hanjie Chen, Faeze Brahman, Xiang Ren +3
Generating free-text rationales is a promising step towards explainable NLP, yet evaluating such rationales remains a challenge. Existing metrics have mostly focused on measuring t…
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
Wanyu Du, Hanjie Chen, Yangfeng Ji
In task-oriented dialogue systems, response generation from meaning representations (MRs) often suffers from limited training examples, due to the high cost of annotating MR-to-Tex…
Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah +1
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance ga…
Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
Hanjie Chen, Yangfeng Ji
Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A commo…
Explaining Predictive Uncertainty by Looking Back at Model Explanations
Hanjie Chen, Wanyu Du, Yangfeng Ji
Predictive uncertainty estimation of pre-trained language models is an important measure of how likely people can trust their predictions. However, little is known about what makes…