Publications

1. The Mismeasure of Man and Models: Evaluating Allocational Harms in Large Language Models
   Hannah Chen, Yangfeng Ji, David Evans
   preprint, 2024
   arXiv  
2. Improve Temporal Awareness of LLMs for Sequential Recommendation
   Zhendong Chu, Zichao Wang, Ruiyi Zhang, Yangfeng Ji, Hongning Wang, Tong Sun
   ICL @ ICML, 2024
   arXiv  
3. Addressing Both Statistical and Causal Gender Fairness in NLP Models
   Hannah Chen, Yangfeng Ji, David Evans
   NAACL Findings, 2024
   ACL Anthology  
4. Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation
   Wanyu Du, Yangfeng Ji
   Preprint, 2023
   arXiv  
5. Secure and Effective Data Appraisal for Machine Learning
   Xu Ouyang, Changhong Yang, Felix Xiaozhu Lin, Yangfeng Ji
   Preprint, 2023
   arXiv  
6. Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values
   Stephanie Schoch, Ritwick Mishra, Yangfeng Ji
   ACL-SRW, 2023
    
7. PLAtE: A Large-scale Dataset for List Page Web Extraction
   Aidan San, Jan Bakus, Colin Lockard, David Ciemiewicz, Yangfeng Ji, Sandeep Atluri, Kevin Small, Heba Elfardy
   ACL (Industry Track), 2023
   arXiv  
8. REV: Information-Theoretic Evaluation of Free-Text Rationales
   Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi and Swabha Swayamdipta
   ACL, 2023
    
9. Efficient NLP Model Finetuning via Data Filtering
   Xu Ouyang, Shahina Mohd Azam Ansari, Felix Xiaozhu Lin, Yangfeng Ji
   IJCAI, 2023
   arXiv  
10. Pre-training Transformers for Knowledge Graph Completion
    Sanxing Chen, Hao Cheng, Xiaodong Liu, Jian Jiao, Yangfeng Ji, Jianfeng Gao
    Preprint, 2023
    arXiv  
11. Does Differential Privacy Impact Bias in Pretrained NLP Models?
    Md Khairul Islam, Andrew Wang, Jieyu Zhao, Yangfeng Ji, Tianhao Wang
    PPAI Workshop @ AAAI, 2023
     
12. Improving Interpretability via Explicit Word Interaction Graph Layer
    Arshdeep Sekhon, Hanjie Chen, Aman Shrivastava, Zhe Wang, Yangfeng Ji, Yanjun Qi
    AAAI, 2023
     
13. Explaining Predictive Uncertainty by Looking Back at Model Explanations
    Hanjie Chen, Wanyu Du, Yangfeng Ji
    UDM Workshop @ AAAI, 2023
     
14. Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification
    Ruixuan Tang, Hanjie Chen, Yangfeng Ji
    The Blackbox NLP Workshop @ EMNLP, 2022
     
15. Balanced Adversarial Training: Balancing Tradeoffs Between Oversensitivity and Undersensitivity in NLP Models
    Hannah Chen, Yangfeng Ji, David Evans
    EMNLP, 2022
     
16. FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows
    Jianqiao Zhao, Yanyang Li, Wanyu Du, Yangfeng Ji, Dong Yu, Michael R. Lyu, Liwei Wang
    EMNLP, 2022
     
17. Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
    Wanyu Du, Hanjie Chen, Yangfeng Ji
    Findings of EMNLP, 2022
     
18. CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification
    Stephanie Schoch, Haifeng Xu, Yangfeng Ji
    NeurIPS, 2022
     
19. White-box Testing of NLP models with Mask Neuron Coverage
    Arshdeep Sekhon, Yangfeng Ji, Matthew B. Dwyer, Yanjun Qi
    Findings of NAACL, 2022
     
20. Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
    Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah, Yangfeng Ji
    Workshop on Insights from Negative Results in NLP, 2022
     
21. Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors
    Wanyu Du, Jianqiao Zhao, Liwei Wang, Yangfeng Ji
    Workshop on Structured Prediction for NLP, 2022
     
22. A Comparison of Explainable Artificial Intelligence Methods in the Phase Classification of Multi-Principal Element Alloys
    Kyungtae Lee, Mukil V Ayyasamy, Yangfeng Ji, Prasanna V Balachandran
    Scientific Reports, 2022
    pdf  
23. Explaining Prediction Uncertainty of Pre-trained Language Models by Detecting Uncertain Words in Inputs
    Hanjie Chen, Yangfeng Ji
    Preprint, 2022
    arXiv  
24. Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
    Hanjie Chen, Yangfeng Ji
    AAAI, 2022
    pdf  
25. Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings
    Andrew Wang, Mohit Sudhakar, Yangfeng Ji
    Preprint, 2021
    arXiv  
26. Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
    Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi
    The BlackBox NLP Workshop @ EMNLP, 2021
    arXiv  
27. HittER: Hierarchical Transformers for Knowledge Graph Embeddings
    Sanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao, Ruofei Zhang, Yangfeng Ji
    EMNLP, 2021
    arXiv  
28. SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
    Wanyu Du, Yangfeng Ji
    The Findings of EMNLP, 2021
    arXiv  
29. Contextualizing Variation in Text Style Transfer Datasets
    Stephanie Schoch, Wanyu Du, Yangfeng Ji
    INLG, 2021
    arXiv  
30. Underreporting of errors in NLG output, and what to do about it
    Emiel van Miltenburg, Miruna-Adriana Clinciu, Ondřej Dušek, Dimitra Gkatzia, Stephanie Inglis, Leo Leppänen, Saad Mahamood, Emma Manning, Stephanie Schoch, Craig Thomson and Luou Wen
    INLG, 2021
     
31. Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
    Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi and Yangfeng Ji
    NAACL, 2021
    ACL Anthology  
32. The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
    Sebastian Gehrmann et al.
    The GEM Workshop, 2021
    arXiv   Project Webpage
33. This is a Problem, Don't You Agree? Framing and Bias in Human Evaluation for Natural Language Generation
    Stephanie Schoch, Diyi Yang, Yangfeng Ji
    The Workshop on Evaluating NLG Evaluation @ INLG, 2020
    ACL Anthology  
34. A Tale of Two Linkings: Dynamically Gating between Schema Linkingand Structural Linking for Text-to-SQL Parsing
    Sanxing Chen, Aidan San, Xiaodong Liu, Yangfeng Ji
    CoLING, 2020
    arXiv   Github
35. Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
    Hanjie Chen, Yangfeng Ji
    EMNLP, 2020
    arXiv   Github
36. Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory
    Hannah Chen, Yangfeng Ji, David Evans
    Findings of EMNLP, 2020
    arXiv   Github
37. Reevaluating Adversarial Examples in Natural Language
    John X. Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji, Yanjun Qi
    Findings of EMNLP, 2020
    arXiv   Github
38. Charging at Second Culmination? Optimal Freemium Pricing for E-books via Field Experiment and Text Analysis
    Yongjun Li, Hanbing Xue, Yangfeng Ji, Natasha Zhang Foutz
    ISMS Marketing Science Conference, 2020
     
39. Familiar Story with (Some) Different Actors? Impact of Content and Execution Similarity on Success of Hedonic Product Line Extension
    Jieqiong Zhang, Yangfeng Ji, Weihe Gao, Natasha Zhang Foutz
    ISMS Marketing Science Conference, 2020
     
40. Pointwise Paraphrase Appraisal is Potentially Problematic
    Hannah Chen, Yangfeng Ji, David Evans
    ACL 2020 Student Research Workshop, 2020
    arXiv  
41. Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
    Hanjie Chen, Guangtao Zheng, Yangfeng Ji
    ACL, 2020
    arXiv   Github
42. Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation
    Hanjie Chen, Yangfeng Ji
    NeurIPS 2019 Workshop on Robust AI in Financial Services, 2019
    arXiv  
43. An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
    Wanyu Du, Yangfeng Ji
    EMNLP, 2019
    arXiv   Github

This page only contains the publications from the UVa ILP lab. For Yangfeng Ji’s publications before 2019, please refer to his academic webpage.