🧑‍🔬 Kai-Wei Chang — all works

100 works · ← Kai-Wei Chang

1. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word EmbeddingsarXiv:1607.06520Tolga Bolukbasi, Kai-Wei Chang, James Zou, et al.2016 · 2,079 citations
2. VisualBERT: A Simple and Performant Baseline for Vision and LanguagearXiv:1908.03557Liunian Harold Li, Mark Yatskar, Da Yin, et al.2019 · 1,568 citations
3. Grounded Language-Image Pre-training ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetLiunian Harold Li et al.2022 · 1,207 citations
4. Gender Bias in Coreference Resolution: Evaluation and Debiasing MethodsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Jieyu Zhao, Tianlu Wang, Mark Yatskar, et al.2018 · 1,202 citations
5. Generating Natural Language Adversarial ExamplesConference on Empirical Methods in Natural Language Processing (EMNLP)Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, et al.2018 · 1,111 citations
6. Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level ConstraintsConference on Empirical Methods in Natural Language Processing (EMNLP)Jieyu Zhao, Tianlu Wang, Mark Yatskar, et al.2017 · 1,050 citations
7. Learn to Explain: Multimodal Reasoning Via Thought Chains for Science Question Answering ↗neural information processing systems · no summary yetPan Lu et al.2022 · 943 citations
8. The Woman Worked as a Babysitter: On Biases in Language GenerationConference on Empirical Methods in Natural Language Processing (EMNLP)Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, et al.2019 · 764 citations
9. Unified Pre-training for Program Understanding and GenerationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, et al.2021 · 750 citations
10. Mitigating Gender Bias in Natural Language Processing: Literature ReviewAnnual Meeting of the Association for Computational Linguistics (ACL)Tony Sun, Andrew Gaut, Shirlyn Tang, et al.2019 · 724 citations
11. Learning Gender-Neutral Word EmbeddingsConference on Empirical Methods in Natural Language Processing (EMNLP)Jieyu Zhao, Yichao Zhou, Zeyu Li, et al.2018 · 520 citations
12. Gender Bias in Contextualized Word EmbeddingsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Jieyu Zhao, Tianlu Wang, Mark Yatskar, et al.2019 · 508 citations
13. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsarXiv:2310.02255Pan Lu, Hritik Bansal, Tony Xia, et al.2023 · 468 citations
14. A Transformer-based Approach for Source Code SummarizationAnnual Meeting of the Association for Computational Linguistics (ACL)Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, et al.2020 · 431 citations
15. Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetTianlu Wang et al.2019 · 393 citations
16. Chameleon: Plug-and-Play Compositional Reasoning with Large Language ModelsConference on Neural Information Processing Systems (NeurIPS)Pan Lu, Baolin Peng, Hao Cheng, et al.2023 · 327 citations
17. Societal Biases in Language Generation: Progress and ChallengesAnnual Meeting of the Association for Computational Linguistics (ACL)Emily Sheng, Kai-Wei Chang, Prem Natarajan, et al.2021 · 257 citations
18. MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?Lecture notes in computer scienceRenrui Zhang, Dongzhi Jiang, Yichi Zhang, et al.2024 · 232 citations
19. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesConference on Empirical Methods in Natural Language Processing (EMNLP)Sunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, et al.2021 · 230 citations
20. DEGREE: A Data-Efficient Generation-Based Event Extraction ModelConference of the North American Chapter of the Association for Computational Linguistics (NAACL)I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, et al.2022 · 227 citations
21. How Much Can CLIP Benefit Vision-and-Language Tasks? ↗arXiv (Cornell University) · no summary yetSheng Shen et al.2021 · 220 citations
22. Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical ReasoningarXiv:2209.14610Pan Lu, Liang Qiu, Kai-Wei Chang, et al.2022 · 219 citations
23. “Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference LettersFindings of the Association for Computational LinguisticsYixin Wan, George Pu, Jiao Sun, et al.2023 · 208 citations
24. Retrieval Augmented Code Generation and SummarizationFindings of the Association for Computational LinguisticsMd Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, et al.2021 · 193 citations
25. Towards Controllable Biases in Language GenerationFindings of the Association for Computational LinguisticsEmily Sheng, Kai-Wei Chang, Prem Natarajan, et al.2020 · 171 citations
26. What Does BERT with Vision Look At? ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetLiunian Harold Li et al.2020 · 171 citations
27. "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters ↗arXiv:2310.09219 · no summary yetYixin Wan et al.2023 · 170 citations
28. SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetDa Yin, Tao Meng, Kai-Wei Chang2020 · 158 citations
29. Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetYichao Zhou et al.2019 · 151 citations
30. A Survey of Deep Learning for Mathematical Reasoning ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetPan Lu et al.2023 · 149 citations
31. Symbolic Chain-of-Thought Distillation: Small Models Can Also “Think” Step-by-StepAnnual Meeting of the Association for Computational Linguistics (ACL)Liunian Harold Li, Jack Hessel, Youngjae Yu, et al.2023 · 140 citations
32. Examining Gender Bias in Languages with Grammatical Gender ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetPei Zhou et al.2019 · 127 citations
33. Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetJieyu Zhao et al.2020 · 115 citations
34. Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetYi Zhou et al.2021 · 105 citations
35. On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language RepresentationsAnnual Meeting of the Association for Computational Linguistics (ACL)Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, et al.2022 · 100 citations
36. Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs ↗Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · no summary yetKuan-Hao Huang, Kai-Wei Chang2021 · 99 citations
37. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryarXiv:2410.10813Di Wu, Hongwei Wang, Wenhao Yu, et al.2024 · 95 citations
38. Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetKuan-Hao Huang et al.2022 · 94 citations
39. The Illinois-Columbia System in the CoNLL-2014 Shared TaskConference on Computational Natural Language Learning (CoNLL)Alla Rozovskaya, Kai-Wei Chang, Mark Sammons, et al.2014 · 94 citations
40. On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing ↗arXiv:1811.00570 · no summary yetWasi Uddin Ahmad et al.2018 · 87 citations
41. The University of Illinois System in the CoNLL-2013 Shared Task ↗Proceedings of the Seventeenth Conference on Computational Natural Language Learning: Shared Task · no summary yetAlla Rozovskaya et al.2013 · 87 citations
42. On Prompt-Driven Safeguarding for Large Language Models ↗arXiv:2401.18018 · no summary yetChujie Zheng et al.2024 · 85 citations
43. How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetHritik Bansal et al.2022 · 83 citations
44. PolicyQA: A Reading Comprehension Dataset for Privacy Policies ↗Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yetWasi Ahmad et al.2020 · 81 citations
45. A Constrained Latent Variable Model for Coreference ResolutionConference on Empirical Methods in Natural Language Processing (EMNLP)Kai-Wei Chang, Rajhans Samdani, Dan Roth2013 · 81 citations
46. Few-Shot Representation Learning for Out-Of-Vocabulary Words ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetZiniu Hu et al.2019 · 80 citations
47. “I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation ↗ACM Conference on Fairness, Accountability, and Transparency (FAccT) · no summary yetAnaelia Ovalle et al.2023 · 79 citations
48. A Joint Framework for Coreference Resolution and Mention Head DetectionConference on Computational Natural Language Learning (CoNLL)Haoruo Peng, Kai-Wei Chang, Dan Roth2015 · 75 citations
49. Model Editing Harms General Abilities of Large Language Models: Regularization to the RescueConference on Empirical Methods in Natural Language Processing (EMNLP)Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, et al.2024 · 67 citations
50. Red Teaming Language Model Detectors with Language ModelsTransactions of the Association for Computational Linguistics (TACL)Zhouxing Shi, Yihan Wang, Fan Yin, et al.2024 · 62 citations
51. Efficient Pattern-Based Time Series Classification on GPU ↗Proceedings · no summary yetKai-Wei Chang et al.2012 · 55 citations
52. Inference Protocols for Coreference ResolutionConference on Computational Natural Language Learning (CoNLL)Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, et al.2011 · 50 citations
53. Agent Lumos: Unified and Modular Training for Open-Source Language Agents ↗arXiv:2311.05657 · no summary yetDa Yin et al.2023 · 49 citations
54. FLIRT: Feedback Loop In-context Red TeamingConference on Empirical Methods in Natural Language Processing (EMNLP)Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, et al.2024 · 42 citations
55. Syntax-augmented Multilingual BERT for Cross-lingual TransferAnnual Meeting of the Association for Computational Linguistics (ACL)Wasi Ahmad, Haoran Li, Kai-Wei Chang, et al.2021 · 42 citations
56. Intent Classification and Slot Filling for Privacy Policies ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetWasi Ahmad et al.2021 · 38 citations
57. Selective block minimization for faster convergence of limited memory large-scale linear models ↗ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · no summary yetKai-Wei Chang, Dan Roth2011 · 33 citations
58. Retrofitting Contextualized Word Embeddings with Paraphrases ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetWeijia Shi et al.2019 · 30 citations
59. Illinois-Coref: The UI System in the CoNLL-2012 Shared Task ↗Joint Conference on EMNLP and CoNLL - Shared Task · no summary yetKai-Wei Chang et al.2012 · 26 citations
60. ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-TranslationKuan-Hao Huang, Varun Iyer, I-Hung Hsu, et al.Machine translation · 24 citations
61. The steerability of large language models toward data-driven personas ↗Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yetJunyi Li et al.2024 · 20 citations
62. Multi-core Structural SVM Training ↗Lecture notes in computer science · no summary yetKai-Wei Chang, Vivek Srikumar, Dan Roth2013 · 19 citations
63. On the steerability of large language models toward data-driven personas ↗arXiv (Cornell University) · no summary yetJunyi Li et al.2023 · 18 citations
64. Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies ↗Findings of the Association for Computational Linguistics: NAACL 2024 · no summary yetAnaelia Ovalle et al.2024 · 17 citations
65. Resolving Ambiguities in Text-to-Image Generative Models ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetNinareh Mehrabi et al.2023 · 16 citations
66. METAL: A Multi-Agent Framework for Chart Generation with Test-Time ScalingAnnual Meeting of the Association for Computational Linguistics (ACL)Bingxuan Li, Yiwei Wang, Jiuxiang Gu, et al.2025 · 15 citations
67. Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies ↗Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · no summary yetMd Rizwan Parvez et al.2023 · 15 citations
68. Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning RepresentationsKuan-Hao Huang, Varun Iyer, Anoop Kumar, et al.Machine translation · 15 citations
69. IllinoisSL: A JAVA Library for Structured Prediction ↗arXiv (Cornell University) · no summary yetKai-Wei Chang et al.2015 · 15 citations
70. When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM ReasoningarXiv:2504.01005Nishad Singhi, Hritik Bansal, Arian Hosseini, et al.2025 · 12 citations
71. PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in EnglishAnnual Meeting of the Association for Computational Linguistics (ACL)Jianfeng Chi, Wasi Uddin Ahmad, Yuan Tian, et al.2023 · 12 citations
72. PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation ↗Findings of the Association for Computational Linguistics: ACL 2023 · no summary yetYixin Wan, Kuan-Hao Huang, Kai-Wei Chang2023 · 10 citations
73. Using Item Response Theory to Measure Gender and Racial Bias of a BERT-based Automated English Speech Assessment SystemWorkshop on Innovative Use of NLP for Building Educational Applications (BEA)Alexander Kwako, Yixin Wan, Jieyu Zhao, et al.2022 · 10 citations
74. Structural Learning with Amortized Inference ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetKai-Wei Chang et al.2015 · 9 citations
75. The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models ↗ACM Conference on Fairness, Accountability, and Transparency (FAccT) · no summary yetAnaelia Ovalle et al.2025 · 8 citations
76. Does BERT Exacerbate Gender or L1 Biases in Automated English Speaking Assessment?Workshop on Innovative Use of NLP for Building Educational Applications (BEA)Alexander Kwako, Yixin Wan, Jieyu Zhao, et al.2023 · 8 citations
77. QUDSELECT: Selective Decoding for Questions Under Discussion ParsingConference on Empirical Methods in Natural Language Processing (EMNLP)Ashima Suvarna, Xiao Liu, Tanmay Parekh, et al.2024 · 7 citations
78. Indirectly Supervised Natural Language Processing ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts) · no summary yetWenpeng Yin et al.2023 · 7 citations
79. A Discriminative Latent Variable Model for Online Clustering ↗International Conference on Machine Learning · no summary yetRajhans Samdani, Kai-Wei Chang, Dan Roth2014 · 7 citations
80. The Hard Positive Truth About Vision-Language Compositionality ↗Lecture notes in computer science · no summary yetAmita Kamath et al.2024 · 6 citations
81. Illinois Cognitive Computation Group UI-CCG TAC 2013 Entity Linking and Slot Filler Validation Systems ↗Theory and applications of categories · no summary yetCheng Xiao et al.2013 · 6 citations
82. Vulnerability of LLMs to Vertically Aligned Text ManipulationsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhecheng Li, Yiwei Wang, Bryan Hooi, et al.2025 · 5 citations
83. Distributed Training of Structured SVM ↗arXiv (Cornell University) · no summary yetChing-pei Lee et al.2015 · 5 citations
84. BILLY: Steering Large Language Models via Merging Persona Vectors for Creative GenerationConference of the European Chapter of the Association for Computational Linguistics (EACL)Tsung-Min Pai, Jui-I Wang, Li-Chun Lu, et al.2026 · 4 citations
85. BLUR: A Bi-Level Optimization Approach for LLM UnlearningConference of the European Chapter of the Association for Computational Linguistics (EACL)Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, et al.2026 · 4 citations
86. JAB: Joint Adversarial Prompting and Belief Augmentation ↗arXiv (Cornell University) · no summary yetNinareh Mehrabi et al.2023 · 4 citations
87. Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning ↗Transactions of the Association for Computational Linguistics · no summary yetAmita Kamath et al.2026 · 3 citations
88. DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal GenerationarXiv:2510.14949Yu Zhou, Sohyun An, Haikang Deng, et al.2025 · 3 citations
89. Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetTao Meng et al.2024 · 3 citations
90. Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation ↗Findings of the Association for Computational Linguistics: ACL 2025 · no summary yetTharindu Kumarage et al.2025 · 2 citations
91. VisRet: Visualization Improves Knowledge-Intensive Text-to-Image RetrievalAnnual Meeting of the Association for Computational Linguistics (ACL)Di Wu, Yixin Wan, Kai-Wei Chang2026 · 1 citation
92. Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular EnglisharXiv:2511.10846Rebecca Dorn, Christina Chance, Casandra Rusti, et al.2025 · 1 citation
93. AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM CodingFindings of the Association for Computational LinguisticsSamuel Osebe, Fan Yang, Junyi Li, et al.2026
94. From Narrow Unlearning to Emergent Misalignment in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, et al.2026
95. InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Yixin Wan, Xingrun Chen, Kai-Wei Chang2026
96. SWAN: Semantic Watermarking with Abstract Meaning RepresentationAnnual Meeting of the Association for Computational Linguistics (ACL)Ziping Ye, Gourab Dey, Christos Christodoulopoulos, et al.2026
97. Inference-Time Control for Trustworthy Large Language Models ↗Preprints.org · no summary yetYuyang Bai et al.2026
98. Open-Domain Safety Policy Construction ↗Findings of the Association for Computational Linguistics: EACL 2026 · no summary yetDi Wu et al.2026
99. Incorporating Fairness in Large Scale NLU Systems ↗no summary yetRahul Gupta et al.2023
100. A Discriminative Latent Variable Model for Clustering of Streaming Data with Application to Coreference Resolution ↗no summary yetRajhans Samdani, Kai-Wei Chang, Dan Roth2013

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kai-wei-chang/works/