Pengfei Hu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
The paper introduces State-Adaptive Prompt Optimization (SAPO), a novel training strategy that treats prompts as dynamic variables to achieve robust fine-tuning, significantly mitigating catastrophic forgetting and improving generalization in LLMs.
Highlighted terms show continued research focus across papers
Papers
cs.CLRecentJun 1, 2026
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
Wenhang Shi, Yiren Chen, Shuqing Bian, Zhe Zhao +4 more
The paper introduces State-Adaptive Prompt Optimization (SAPO), a novel training strategy that treats prompts as dynamic variables to achieve robust fine-tuning, significantly mitigating catastrophic…
View →