Shuang Liu

Shuang Liu

Ph.D. Student · School of Computer Science, Carnegie Mellon University

✉ Email Google Scholar LinkedIn

About Me

I am a third-year Ph.D. student in the School of Computer Science at Carnegie Mellon University (CMU), advised by Sarah Scheffler. I am a member of CyLab, the security and privacy institute at CMU. Before studying at CMU, I obtained my bachelor’s degree from Tsinghua University. I went on to earn master’s degrees from the University of Pennsylvania (M.S. in Computer and Information Technology) and the University of California, Berkeley (LL.M. in Technology and Law).

Research Interest

Reward modeling and RLHF robustness; LLM post-training and alignment; LLM evaluation and agents (benchmarks and user simulation); synthetic data generation; trustworthy and responsible AI; ML privacy and safety; AI governance and legal AI.

Publications

Preprints

Main figure of BiasReducer arXiv 2026
BiasReducer: Adaptive Bias Mitigation for Reward Models
Shuang Liu, Yongliang Miao, Yanguang Liu, Haoyi Xiong, and Mengnan Du
arXiv preprint, 2026
Paper
Main figure of Look Before You Select arXiv 2026
Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation
Yongliang Miao, Shuang Liu, Yanguang Liu, Yandong Bai, and Mengnan Du
arXiv preprint, 2026
Paper
Main figure of RewardExplainer arXiv 2026
RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback
Jingyi He, Nier Wu, Shuang Liu, Xin Wang, Mengnan Du, and Xia Hu
arXiv preprint, 2026
Paper

Conference Papers

Main figure of HARVE EMNLP 2026
HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models
Shuang Liu, Yuxuan Bo, Qiuyang Zhao, Caiyue Huang, Xiaorong Chen, Yanguang Liu, and Mengnan Du
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Main Conference
Paper Code
Main figure of LLM Agents in Law ACL 2026
LLM Agents in Law: Taxonomy, Applications, and Challenges
Shuang Liu, Ruijia Zhang, Ruoyun Ma, Yujia Deng, Lanyi Zhu, Jiayu Li, Zelong Li, Zhibin Shen, and Mengnan Du
Annual Meeting of the Association for Computational Linguistics (ACL), 2026 (Main Conference)
Paper
Main figure of Adequately Tailoring Age Verification Regulations CSLAW 2026
Adequately Tailoring Age Verification Regulations
Shuang Liu and Sarah Scheffler
The ACM Symposium on Computer Science and Law, 2026
Paper
Main figure of ContractEval NLLP 2025
ContractEval: Benchmarking LLMs for Legal Risk Identification in Commercial Contracts
Shuang Liu, Zelong Li, Ruoyun Ma, Haiyan Zhao, and Mengnan Du
The 7th Workshop on Natural Legal Language Processing, 2025
🏆 Best Presentation Award
Paper Code
Main figure of Privacy-preserving Age Verification based on Improved Verifiable Credentials Framework ConPro 2025
Privacy-preserving Age Verification based on Improved Verifiable Credentials Framework
Shuang Liu and Sarah Scheffler
9th Workshop on Technology and Consumer Protection (ConPro ’25), 2025
Paper

Journal Articles

Buffalo Law Review
Deepfake & Deepfaith
Jiawei Zhang* and Shuang Liu* (*equal contribution)
Buffalo Law Review, 2026
Paper

Recent Talks