Sharon Li

18 papers A* 5Journal 11Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability.
CoRR
Shawn Im, Changdae Oh, Zhen Fang, Sharon Li
2026 J jnl
ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation.
CoRR
Hyeong Kyu Choi, Sharon Li
2026 J jnl
Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents.
CoRR
Changdae Oh, Seongheon Park, To Eun Kim, Jiatong Li, Wendi Li, Samuel Yeh, Xuefeng Du, Hamed Hassani, Paul Bogdan, Dawn Song, Sharon Li
2026 J jnl
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation.
CoRR
Seongheon Park, Changdae Oh, Hyeong Kyu Choi, Xuefeng Du, Sharon Li
2025 J jnl
A Definition of AGI.
CoRR
Dan Hendrycks, Dawn Song, Christian Szegedy, Honglak Lee, Yarin Gal, Erik Brynjolfsson, Sharon Li, Andy Zou, Lionel Levine, Bo Han, Jie Fu, Ziwei Liu, Jinwoo Shin, Kimin Lee, Mantas Mazeika, Long Phan, George Ingebretsen, Adam Khoja, Cihang Xie, Olawale Salaudeen, Matthias Hein, Kevin Zhao, Alexander Pan, David Duvenaud, Bo Li, Steve Omohundro, Gabriel Alfour, Max Tegmark, Kevin McGrew, Gary Marcus, Jaan Tallinn, Eric Schmidt, Yoshua Bengio
2025 J jnl
Detecting Distillation Data from Reasoning Models.
CoRR
Hengxiang Zhang, Hyeong Kyu Choi, Sharon Li, Hongxin Wei
2025 J jnl
How Well Can Preference Optimization Generalize Under Noisy Feedback?
CoRR
Shawn Im, Sharon Li
2025 J jnl
KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning.
CoRR
Yinyi Luo, Zhexian Zhou, Hao Chen, Kai Qiu, Marios Savvides, Sharon Li, Jindong Wang
2025 J jnl
Measuring and Mitigating Identity Bias in Multi-Agent Debate via Anonymization.
CoRR
Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li
2025 J jnl
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary.
CoRR
Zhaolong Su, Wang Lu, Hao Chen, Sharon Li, Jindong Wang
2024 A* conf
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment.
NeurIPS
Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Sharon Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao
2024 A* conf
Bridging OOD Detection and Generalization: A Graph-Theoretic View.
NeurIPS
Han Wang, Sharon Li
2024 — conf
DCAI: Data-centric Artificial Intelligence.
WWW (Companion Volume)
Wei Jin, Haohan Wang, Daochen Zha, Qiaoyu Tan, Yao Ma, Sharon Li, Su-In Lee
2024 A* conf
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection.
NeurIPS
Xuefeng Du, Chaowei Xiao, Sharon Li
2024 A* conf
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models.
NeurIPS
Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Sharon Li, Neel Joshi
2023 — conf
Designing Fair AI Systems: Exploring the Interaction of Explainable AI and Task Objectivity on Users' Fairness Perception.
PACIS
Tingru Cui, Sharon Li, Kaiping Chen, James Bailey, Feng Liu
2021 A* conf
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation.
ICLR
Karan Goel, Albert Gu, Sharon Li, Christopher Ré
2020 J jnl
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation.
CoRR
Karan Goel, Albert Gu, Sharon Li, Christopher Ré