Research interests and publications
Wang, C., Fan, C., Zhang, Y., Jia, J., Wei, D., Ram, P., Baracaldo, N. and Liu, S. (2025) Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills. EMNLP. paper
Wang, C., Zhang, Y., Jia, J., Ram, P., Wei, D., Yao, Y., Pal, S., Baracaldo, N. and Liu, S. (2025) Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning. International Conference on Machine Learning. paper
Jia, J., Liu, J., Zhang, Y., Ram, P., Baracaldo, N. and Liu, S. (2024) WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models. Advances in Neural Information Processing Systems. paper
Jia, J., Liu, J., Ram, P., Yao, Y., Liu, G., Liu, Y., Sharma, P., and Liu, S. (2023). Model sparsification can simplify machine unlearning. Advances of Neural Information Processing Systems. paper arXiv.