כתבה
arXiv cs.CL ·
CROCODIL: עריכת קוד רב-מודלים
CROCODIL: Cross-Model Code Editing with LLMs
CROCODIL הוא פרקטיקה חדשה שמטרתה לקצץ בעריכות יתר בקוד שנוצר על ידי LLMs. הפרקטיקה נכתבה על ידי צוות EngineeringSoftware ומיועדת לשיפור תפעוליות של LLMs.
תקציר מקורי באנגליתarXiv:2609.03894v1 Announce Type: new Abstract: Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may prefer different models, and individual developers may switch between models across different coding sessions. Because of this, the edits any one model makes are frequently applied to foreign code originally generated by another model. These LLMs are often trained on different datasets, and as a result have different stylistic preferences. Do LLMs behave differently when they edit foreign code originally written by a different LLM with a different coding style? We find that models tend to make more, and often excessive, edits on foreign code. We introduce CROCODIL (Cr
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית