{"ID":2846478,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01192","arxiv_id":"2511.01192","title":"DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection","abstract":"Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current approaches often degrades significantly under domain shift. To address this challenge, we propose a novel framework designed to capture both domain-specific and domain-general MGT patterns through a two-stage Disentangled mixturE-of-ExpeRts (DEER) architecture. First, we introduce a disentangled mixture-of-experts module, in which domain-specific experts learn fine-grained, domain-local distinctions between human and machine-generated text, while shared experts extract transferable, cross-domain features. Second, to mitigate the practical limitation of unavailable domain labels during inference, we design a reinforcement learning-based routing mechanism that dynamically selects the appropriate experts for each input instance, effectively bridging the train-inference gap caused by domain uncertainty. Extensive experiments on five in-domain and five out-of-domain benchmark datasets demonstrate that DEER consistently outperforms state-of-the-art methods, achieving average F1-score improvements of 1.39% and 5.32% on in-domain and out-of-domain datasets respectively, along with accuracy gains of 1.35% and 3.61% respectively. Ablation studies confirm the critical contributions of both disentangled expert specialization and adaptive routing to model performance.","short_abstract":"Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current approaches often degrades significantly under domain shift. To address this challenge...","url_abs":"https://arxiv.org/abs/2511.01192","url_pdf":"https://arxiv.org/pdf/2511.01192v1","authors":"[\"Guoxin Ma\",\"Xiaoming Liu\",\"Zhanhan Zhang\",\"Chengzhengxu Li\",\"Shengchao Liu\",\"Yu Lan\"]","published":"2025-11-03T03:36:48Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Mixture of Experts\",\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}