Skip to content
arXiv cs.CL · Papers

Decoupling Task-Solving and Output Formatting in LLM Generation

arXiv:2510.03595v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when prompts intertwine task instructions with rigid formatting requirements. This entanglemen