2025
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin.
CoRR, June, 2025

GPT as a Monte Carlo Language Tree: A Probabilistic Perspective.
CoRR, January, 2025

PiCO: Peer Review in LLMs based on Consistency Optimization.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Is Parameter Collision Hindering Continual Learning in LLMs?
Proceedings of the 31st International Conference on Computational Linguistics, 2025

2024
Sequential Cooperative Distillation for Imbalanced Multi-Task Learning.
J. Comput. Sci. Technol., September, 2024

Sparse Orthogonal Parameters Tuning for Continual Learning.
CoRR, 2024

Peer-review-in-LLMs: Automatic Evaluation Method for LLMs in Open-environment.
CoRR, 2024

2023
LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.
CoRR, 2023

Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023