3 papers
cs.CL2026
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
Shaoxiong Zhan, Yanlin Lai, Ziyu Lu +3
Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data.…
cs.CL2025
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
Yike Zhao, Simin Guo, Ziqing Yang +3
The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various propo…
cs.CL2025
Consultant Decoding: Yet Another Synergistic Mechanism
Chuanghao Ding, Jiaping Wang, Ziqing Yang +4
The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language…