Search Results for author: Hanjie Chen

Found 16 papers, 9 papers with code

RORA: Robust Free-Text Rationale Evaluation

no code implementations28 Feb 2024 Zhengping Jiang, Yining Lu, Hanjie Chen, Daniel Khashabi, Benjamin Van Durme, Anqi Liu

This is achieved by assessing the conditional V-information \citep{hewitt-etal-2021-conditional} with a predictive family robust against leaky features that can be exploited by a small model.

Decision Making

Explainability for Large Language Models: A Survey

no code implementations2 Sep 2023 Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du

For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.

Improving Interpretability via Explicit Word Interaction Graph Layer

1 code implementation3 Feb 2023 Arshdeep Sekhon, Hanjie Chen, Aman Shrivastava, Zhe Wang, Yangfeng Ji, Yanjun Qi

Recent NLP literature has seen growing interest in improving model interpretability.

KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales

no code implementations19 Dec 2022 Aaron Chan, Zhiyuan Zeng, Wyatt Lake, Brihi Joshi, Hanjie Chen, Xiang Ren

First, KNIFE finetunes a teacher LM (given task input and FTR) to predict the task output, transferring reasoning knowledge from the FTRs to the teacher's hidden states.

Knowledge Distillation Language Modelling +1

REV: Information-Theoretic Evaluation of Free-Text Rationales

1 code implementation10 Oct 2022 Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha Swayamdipta

More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.

Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation

1 code implementation19 May 2022 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-Text pairs.

Dialogue Generation Language Modelling +2

Pathologies of Pre-trained Language Models in Few-shot Fine-tuning

no code implementations insights (ACL) 2022 Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah, Yangfeng Ji

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 gain comes from.

text-classification Text Classification

Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation

1 code implementation23 Mar 2022 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.

text-classification Text Classification

Explaining Predictive Uncertainty by Looking Back at Model Explanations

no code implementations11 Jan 2022 Hanjie Chen, Wanyu Du, Yangfeng Ji

Explaining predictive uncertainty is an important complement to explaining prediction labels in helping users understand model decision making and gaining their trust on model predictions, while has been largely ignored in prior works.

Decision Making Natural Language Inference +2

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

1 code implementation EMNLP (BlackboxNLP) 2021 Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi

Via a small portion of word-level swaps, these adversarial perturbations aim to make the resulting text semantically and spatially similar to its seed input (therefore sharing similar interpretations).

Language Modelling

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

1 code implementation NAACL 2021 Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji

Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features.

Natural Language Inference Paraphrase Identification +1

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

3 code implementations EMNLP 2020 Hanjie Chen, Yangfeng Ji

To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations.

General Classification text-classification +1

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection

2 code implementations ACL 2020 Hanjie Chen, Guangtao Zheng, Yangfeng Ji

Experiments show the effectiveness of the proposed method in providing explanations that are both faithful to models and interpretable to humans.

Decision Making General Classification +2

Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation

no code implementations10 Sep 2019 Hanjie Chen, Yangfeng Ji

Experiments show the proposed data augmentation methods significantly improve the explainability of both neural classifiers.

Data Augmentation General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.