FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generation

Lu Han, Jingyao Zhang, Katy Ilonka Gero, Nguyen H. Tran

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 benchmark and ASCE-independent external authorship verification. Using this protocol, we find that common federated PEFT baselines can preserve semantic utility while averaging out author-specific signals. To address this homogenization, we instantiate FAVoR (Federated Authorial Voice Retention), an author-style residual mechanism for federated PEFT. FAVoR uses a shared-private adapter design: clients upload shared-adapter updates while…