כתבה
arXiv cs.CL ·
FAVoR: חיסול ומניעת התאחדות סגנון-כותב באדפטציה פדרטיבית
FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generation
ניתוח והתמודדות עם התאחדות סגנון-כותב באדפטציה פדרטיבית לפרסומים אישיים. נעשה שימוש ב-GPT-5.
תקציר מקורי באנגליתarXiv:2609.30968v1 Announce Type: new Abstract: Large language models are increasingly used as personalized writing assistants, but adapting a model across many authors can compromise individual writing style by pulling author-specific signals toward a shared register. Federated parameter-efficient fine-tuning (PEFT) offers a data-local setting for this multi-author adaptation problem: clients keep author text local while sharing compact adapter updates. However, we show that standard aggregation can preserve continuation utility while making different authors' generations less distinguishable in style space, a failure mode we define as author-style homogenization. We evaluate author-style retention with Angular Style Classification Encoder (ASCE)-based diagnostics on our main BlogText ben
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית