# When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer Source: [When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer]() Collection index: [llms.txt]() Data updated: 2026-06-06T05:00:04.316Z Authors: Zhen Sun, Yifan Liao, Zhicong Huang, Jiaheng Wei, Cheng Hong, Yutao Yue, Xinlei He Published: 2026-06-04T02:50:58.000Z ## Abstract Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and misuse investigation. As new large language models continue to emerge, attribution models must continuously incorporate new generators while preserving their ability to recognize previously seen ones. Prior works have shown that this lifelong MGT attribution setting is challenging, and existing methods often struggle to achieve a stable balance between adapting to new classes and retaining old ones. To address this issue, we propose RidgeFT, a lightweight analytic update framework that does not rely on exemplar replay. RidgeFT trains a task-aware encoder on the initial generator set, stores compact class-wise sufficient statistics when each generator class is first observed, and then freezes the encoder for replay-free closed-form updates. It then suppresses generator-irrelevant variation through covariance calibration, improves representation capacity with fixed random features, and updates new classes through closed-form ridge regression based on class-level sufficient statistics. Across multi-topic evaluations with varying initial generator setups, RidgeFT consistently outperforms baselines. It achieves the best macro-F1 across domains, backbones, and incremental protocols, while also improving both old-class retention and new-class adaptation. These results suggest that feature-stable analytic updates provide a simple yet effective approach to lifelong MGT attribution. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Machine-Generated Text Attribution on STEM](): Machine-Generated Text Attribution; STEM; Full Macro F1: 91.9. - [Machine-Generated Text Attribution on Humanities](): Machine-Generated Text Attribution; Humanities; Full Macro-F1: 88.1. - [Machine-Generated Text Attribution on AIGTBench](): Machine-Generated Text Attribution; AIGTBench; Macro F1 (Full): 91.5. - [Machine-Generated Text Attribution on Social Science](): Machine-Generated Text Attribution; Social Science; Full Macro-F1: 88. ## Original sources and implementation [Original paper]() [PDF]()