To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing May 8, 2026· Wei Cheng , Yongchang Cao , Chen Shen , Binhua Li , Jue Chen , Yongbin Li Wei Hu · 0 min read Cite URL Type Conference paper Publication Findings of the Association for Computational Linguistics: ACL 2026 Last updated on May 8, 2026 Authors Wei Hu Nanjing University School of Computer Science ← Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers May 8, 2026 Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation May 8, 2026 →