GPT as a Monte Carlo Language Tree: A Probabilistic Perspective.
CoRR, January, 2025
Is Parameter Collision Hindering Continual Learning in LLMs?
Proceedings of the 31st International Conference on Computational Linguistics, 2025
Sparse Orthogonal Parameters Tuning for Continual Learning.
CoRR, 2024
Peer-review-in-LLMs: Automatic Evaluation Method for LLMs in Open-environment.
CoRR, 2024
Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation.
Proceedings of the Computer Vision - ECCV 2024, 2024
Towards Better Seach Query Classification with Distribution-Diverse Multi-Expert Knowledge Distillation in JD Ads Search.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024
LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.
CoRR, 2023
Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search.
CoRR, 2023
Active Learning for Open-set Annotation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Co-Imitation Learning without Expert Demonstration.
CoRR, 2021
Asynchronous Active Learning with Distributed Label Querying.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
Reinforcement Learning with Supervision from Noisy Demonstrations.
CoRR, 2020