Yixin Wan

38 papers A* 3A 1Journal 22Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues.
CoRR
Zheyuan Liu, Dongwhi Kim, Yixin Wan, Xiangchi Yuan, Zhaoxuan Tan, Fengran Mo, Meng Jiang
2025 J jnl
CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback.
CoRR
Yixin Wan, Kai-Wei Chang
2025 J jnl
Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries.
CoRR
Jen-tse Huang, Yuhang Yan, Linqi Liu, Yixin Wan, Wenxuan Wang, Kai-Wei Chang, Michael R. Lyu
2025 — conf
LUME: LLM Unlearning with Multitask Evaluations.
EMNLP (Findings)
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025 J jnl
LUME: LLM Unlearning with Multitask Evaluations.
CoRR
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025 A* conf
MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations.
ICLR
Shaochen (Henry) Zhong, Yifan Lu, Lize Shao, Bhargav Bhushanam, Xiaocong Du, Yixin Wan, Yucheng Shi, Daochen Zha, Yiwei Wang, Ninghao Liu, Kaixiong Zhou, Shuai Xu, Kai-Wei Chang, Louis Feng, Vipin Chaudhary, Xia Hu
2025 J jnl
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing.
CoRR
Yixin Wan, Lei Ke, Wenhao Yu, Kai-Wei Chang, Dong Yu
2025 — conf
Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models.
EMNLP (Findings)
Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta
2025 J jnl
Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning.
CoRR
Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta
2025 J jnl
SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models.
CoRR
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
2025 — conf
The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects.
ACL (1)
Yixin Wan, Kai-Wei Chang
2025 — conf
V-ALPHASOCIAL: Benchmark and Self-Reflective Chain-of-Thought Generation for Visual Social Commonsense Reasoning.
ACL (Findings)
Zongyu Lin, Zhikun Xu, Xiaohan Song, Yixin Wan, Xingcheng Yao, Tsung-Han Lin, Selina Song, Pranav Subbaraman, Ben Zhou, Kai-Wei Chang, Yizhou Sun
2025 J jnl
Visualized Text-to-Image Retrieval.
CoRR
Di Wu, Yixin Wan, Kai-Wei Chang
2025 — conf
Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases.
EMNLP (Findings)
Jen-tse Huang, Yuhang Yan, Linqi Liu, Yixin Wan, Wenxuan Wang, Kai-Wei Chang, Michael R. Lyu
2025 J jnl
Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs.
CoRR
Yixin Wan, Xingrun Chen, Kai-Wei Chang
2025 — conf
White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs.
ACL (1)
Yixin Wan, Kai-Wei Chang
2024 — conf
MACAROON: Training Vision-Language Models To Be Your Engaged Partners.
EMNLP (Findings)
Shujin Wu, Yi Fung, Sha Li, Yixin Wan, Kai-Wei Chang, Heng Ji
2024 J jnl
MACAROON: Training Vision-Language Models To Be Your Engaged Partners.
CoRR
Shujin Wu, Yi R. Fung, Sha Li, Yixin Wan, Kai-Wei Chang, Heng Ji
2024 J jnl
Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation.
CoRR
Yixin Wan, Arjun Subramonian, Anaelia Ovalle, Zongyu Lin, Ashima Suvarna, Christina Chance, Hritik Bansal, Rebecca Pattichis, Kai-Wei Chang
2024 A* conf
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention.
EMNLP
Yixin Wan, Di Wu, Haoran Wang, Kai-Wei Chang
2024 J jnl
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention.
CoRR
Yixin Wan, Di Wu, Haoran Wang, Kai-Wei Chang
2024 J jnl
The Male CEO and the Female Assistant: Probing Gender Biases in Text-To-Image Models Through Paired Stereotype Test.
CoRR
Yixin Wan, Kai-Wei Chang
2024 J jnl
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory.
CoRR
Eric Hanchen Jiang, Yasi Zhang, Zhi Zhang, Yixin Wan, Andrew Lizarraga, Shufan Li, Ying Nian Wu
2024 J jnl
White Men Lead, Black Women Help: Uncovering Gender, Racial, and Intersectional Bias in Language Agency.
CoRR
Yixin Wan, Kai-Wei Chang
2023 — conf
"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters.
EMNLP (Findings)
Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng
2023 J jnl
"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters.
CoRR
Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng
2023 A conf
ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression.
INTERSPEECH
Yixin Wan, Yuan Zhou, Xiulian Peng, Kai-Wei Chang, Yan Lu
2023 J jnl
ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression.
CoRR
Yixin Wan, Yuan Zhou, Xiulian Peng, Kai-Wei Chang, Yan Lu
2023 — conf
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems.
EMNLP (Findings)
Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang
2023 J jnl
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems.
CoRR
Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang
2023 — conf
Does BERT Exacerbate Gender or L1 Biases in Automated English Speaking Assessment?
BEA@ACL
Alexander Kwako, Yixin Wan, Jieyu Zhao, Mark Hansen, Kai-Wei Chang, Li Cai
2023 — conf
PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation.
ACL (Findings)
Yixin Wan, Kuan-Hao Huang, Kai-Wei Chang
2023 J jnl
PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation.
CoRR
Yixin Wan, Kuan-Hao Huang, Kai-Wei Chang
2023 J jnl
Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation.
CoRR
Yixin Wan, Fanyou Wu, Weijie Xu, Srinivasan H. Sengamedu
2023 A* conf
TheoremQA: A Theorem-driven Question Answering Dataset.
EMNLP
Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia
2023 J jnl
TheoremQA: A Theorem-driven Question Answering dataset.
CoRR
Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia
2022 — conf
Improving the Adversarial Robustness of NLP Models by Information Bottleneck.
ACL (Findings)
Cenyuan Zhang, Xiang Zhou, Yixin Wan, Xiaoqing Zheng, Kai-Wei Chang, Cho-Jui Hsieh
2022 J jnl
Improving the Adversarial Robustness of NLP Models by Information Bottleneck.
CoRR
Cenyuan Zhang, Xiang Zhou, Yixin Wan, Xiaoqing Zheng, Kai-Wei Chang, Cho-Jui Hsieh