Publications

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models

Published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), 2025

Chengao Li, Hanyu Zhang, Yunkun Xu, Hongyan Xue, Xiang Ao, and Qing He.

Recommended citation: Chengao Li, Hanyu Zhang, Yunkun Xu, Hongyan Xue, Xiang Ao, and Qing He. 2025. Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11214–11232, Vienna, Austria. Association for Computational Linguistics.
Download Paper

Controlling large language models through concept activation vectors

Published in Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025), 2025

Hanyu Zhang, Xiting Wang, Chengao Li, Xiang Ao, Qing He.

Recommended citation: Zhang, H., Wang, X., Li, C., Ao, X., & He, Q. (2025). Controlling Large Language Models Through Concept Activation Vectors. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25851-25859.
Download Paper

White Book on Safety Evaluation of Generative Large Models (2024)

Published in CCF China Data 2024, 2024

State Key Laboratory of AI Safety, Chinese Academy of Sciences; The Third Research Institute of Ministry of Public Security; Ant Security Lab.