Publications

1. Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMs
   Pengda Wang*, Zilin Xiao*, Hanjie Chen, Frederick L. Oswald
   Preprint. [arXiv]


2. Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions
   Hanjie Chen*, Zhouxiang Fang*, Yash Singla, Mark Dredze
   Preprint. [arXiv]


3. RORA: Robust Free-Text Rationale Evaluation
   Zhengping Jiang*, Yining Lu*, Hanjie Chen, Daniel Khashabi, Benjamin Van Durme, Anqi Liu
   Preprint. [arXiv]


4. Explainability for Large Language Models: A Survey
   Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
   ACM Transactions on Intelligent Systems and Technology, Jan. 2024. [Paper]


5. REV: Information-Theoretic Evaluation of Free-Text Rationales
   Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, and Swabha Swayamdipta
   The 61st Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, Jul. 2023
   [Acceptance Rate: 1074/4864≈22%][Paper] [Code]


6. KNIFE: Knowledge Distillation with Free-Text Rationales
   Aaron Chan*, Zhiyuan Zeng*, Wyatt Lake, Brihi Joshi, Hanjie Chen, Xiang Ren
   Preprint. [arXiv]


7. Neural Model Interpretability for Natural Language Processing
   Hanjie Chen
   PhD Dissertation, May 2023


8. Improving Interpretability via Explicit Word Interaction Graph Layer
   Arshdeep Sekhon, Hanjie Chen, Aman Shrivastava, Zhe Wang, Yangfeng Ji, Yanjun Qi
   The 37th AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, USA, Feb. 2023.
   [Acceptance Rate: 1721/8777≈19.6%][Paper][Code]


9. Explaining Predictive Uncertainty by Looking Back at Model Explanations
   Hanjie Chen, Wanyu Du, Yangfeng Ji
   AAAI Workshop on Uncertainty Reasoning and Quantification in Decision Making, Feb. 2023. [Paper]


10. Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification.
    Ruixuan Tang, Hanjie Chen, Yangfeng Ji
    EMNLP BlackboxNLP Workshop, Dec. 2022 [Paper]


11. Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
    Wanyu Du, Hanjie Chen, Yangfeng Ji
    Findings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, Dec. 2022. [Paper][Code]


12. Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
    Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah, Yangfeng Ji
    ACL Workshop on Insights from Negative Results in NLP, Dublin, Ireland, May 2022. [Paper]


13. Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
    Hanjie Chen, Yangfeng Ji
    The 36th AAAI Conference on Artificial Intelligence (AAAI), Vancouver, BC, Canada, Feb. 2022.
    [Acceptance Rate: 1349/9020≈15%, Oral Presentation (top 1.5%)] [Paper] [Code]


14. Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
    Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi
    EMNLP BlackboxNLP Workshop, Nov. 2021 [Paper]


15. Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
    Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji
    2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Jun. 2021
    [Acceptance Rate: 477/1797≈26.5%] [Paper] [Code]


16. Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
    Hanjie Chen, Yangfeng Ji
    The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 2020
    [Acceptance Rate: 754/3359≈22.4%] [Paper] [Code]


17. Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
    Hanjie Chen, Guangtao Zheng, Yangfeng Ji
    The 58th Annual Meeting of the Association for Computational Linguistics (ACL), July 2020
    [Acceptance Rate: 779/3429≈22.7%] [Paper] [Code]


18. Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation
    Hanjie Chen, Yangfeng Ji
    NeurIPS 2019 Workshop on Robust AI in Financial Services, Dec. 2019 [Paper]