Yang Zhao

14 papers Journal 10Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration.
CoRR
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
2026 J jnl
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization.
CoRR
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
2025 — conf
Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns.
ACL (1)
Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin
2025 J jnl
Benchmarking and Pushing the Multi-Bias Elimination Boundary of LLMs via Causal Effect Estimation-guided Debiasing.
CoRR
Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Yang Zhao, Bing Qin, Ting Liu
2025 — conf
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection.
ACL (1)
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
2025 J jnl
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection.
CoRR
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
2025 J jnl
Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models.
CoRR
Zhouhao Sun, Xiao Ding, Li Du, Yunpeng Xu, Yixuan Ma, Yang Zhao, Bing Qin, Ting Liu
2025 J jnl
Think straight or think again? Continual joint learning of deduction, abduction and induction.
Neural Networks
Kai Xiong, Xiao Ding, Yixin Cao, Yang Zhao, Ting Liu, Bing Qin
2025 J jnl
UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection.
CoRR
Yang Zhao, Kai Xiong, Xiao Ding, Li Du, YangouOuyang, Zhouhao Sun, Jiannan Guan, Wenbin Zhang, Bin Liu, Dong Hu, Bing Qin, Ting Liu
2024 — conf
Causal-Guided Active Learning for Debiasing Large Language Models.
ACL (1)
Zhouhao Sun, Li Du, Xiao Ding, Yixuan Ma, Yang Zhao, Kaitao Qiu, Ting Liu, Bing Qin
2024 J jnl
Causal-Guided Active Learning for Debiasing Large Language Models.
CoRR
Li Du, Zhouhao Sun, Xiao Ding, Yixuan Ma, Yang Zhao, Kaitao Qiu, Ting Liu, Bing Qin
2024 — conf
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning.
ACL (Findings)
Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Shi Jun, Ting Liu, Bing Qin
2024 J jnl
Deciphering the lmpact of Pretraining Data on Large Language Models through Machine Unlearning.
CoRR
Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Jun Shi, Ting Liu, Bing Qin
2024 J jnl
Supervised Fine-Tuning: An Activation Pattern Optimization Process for Attention Heads.
CoRR
Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin