Profiles2019-2026
Kai Wei Chang
University of California, Los Angeles
Also published as Kai-Wei Chang
87Papers
39Last author
129Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers87
- VisRet: Visualization Improves Knowledge-Intensive Text-to-Image RetrievalAuthor 3 of 3ACL 2026 · 3 citations
- BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop ReasoningAuthor 5 of 6ACL Findings 2026
- InsideOut: Measuring and Mitigating Insider-Outsider Bias in Interview Script GenerationAuthor 3 of 3ACL 2026
- The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual SubjectsAuthor 2 of 2ACL 2025 · 11 citations
- White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMsAuthor 2 of 2ACL 2025 · 9 citations
- DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM ReasoningAuthor 4 of 5EMNLP 2025 · 1 citation
- SNaRe: Domain-aware Data Generation for Low-Resource Event DetectionAuthor 6 of 7EMNLP 2025 · 1 citation
- Controllable Generation via Locally Constrained ResamplingAuthor 2 of 3ICLR 2025
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryAuthor 5 of 6ICLR 2025
- Matryoshka Query Transformer for Large Vision-Language ModelsAuthor 6 of 6NeurIPS 2024 · 58 citations
- Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with DataAuthor 5 of 6ACL Findings 2024 · 25 citations
- TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event ExtractionAuthor 7 of 9ACL Findings 2024 · 16 citations
- SafeWorld: Geo-Diverse Safety AlignmentAuthor 4 of 5NeurIPS 2024 · 14 citations
- Model Editing Harms General Abilities of Large Language Models: Regularization to the RescueAuthor 6 of 7EMNLP 2024 · 8 citations
- KPEval: Towards Fine-Grained Semantic-Based Keyphrase EvaluationAuthor 3 of 3ACL Findings 2024 · 7 citations
- Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented GenerationAuthor 5 of 5EMNLP 2024 · 6 citations
- SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and PreparednessAuthor 7 of 9EMNLP 2024 · 4 citations
- MetaKP: On-Demand Keyphrase GenerationAuthor 3 of 3EMNLP Findings 2024 · 3 citations
- The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented InterventionAuthor 4 of 4EMNLP 2024 · 3 citations
- Re-ReST: Reflection-Reinforced Self-Training for Language AgentsAuthor 4 of 5EMNLP 2024 · 2 citations
- Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless PredictionsAuthor 8 of 8ACM MM 2024 · 1 citation
- VDebugger: Harnessing Execution Feedback for Debugging Visual ProgramsAuthor 7 of 7EMNLP Findings 2024 · 1 citation
- Attribute Controlled Fine-tuning for Large Language Models: A Case Study on DetoxificationAuthor 7 of 9EMNLP Findings 2024
- VideoCon: Robust Video-Language Alignment via Contrast CaptionsAuthor 4 of 5CVPR 2024
- "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference LettersAuthor 5 of 6EMNLP Findings 2023 · 139 citations
- CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive LearningAuthor 5 of 5ICCV 2023 · 78 citations
- AVATAR: A Parallel Corpus for Java-Python Program TranslationAuthor 5 of 6ACL Findings 2023 · 46 citations
- IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language ModelsAuthor 7 of 8EMNLP Findings 2023 · 46 citations
- DesCo: Learning Object Recognition with Rich Language DescriptionsAuthor 5 of 5NeurIPS 2023 · 38 citations
- What's "up" with vision-language models? Investigating their struggle with spatial reasoningAuthor 3 of 3EMNLP 2023 · 31 citations
Showing the 30 most recent indexed papers.
