Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
Yaoning Yu, Ye Yu, Peiyan Zhang +3
Prompt quality plays a critical role in the performance of large language models (LLMs), motivating a growing body of work on prompt optimization. Most existing methods optimize pr…
cs.CL2025
PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models
Ye Yu, Yaoning Yu, Haohan Wang
Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning, but the…