aiqbench analysis
RidgeFT introduces a lightweight, replay-free framework for lifelong machine-generated text attribution that effectively balances adapting to new models while retaining accuracy on previously seen ones. By utilizing closed-form updates and covariance calibration, the method achieves superior macro-F1 scores across diverse domains and backbones without the computational overhead of storing exemplars. This approach offers a practical solution for maintaining model accountability in rapidly evolving AI landscapes where new generators emerge frequently.
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
arXiv:2606.05626v1 Announce Type: cross 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.
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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2606.05626 [cs.CL]
(or arXiv:2606.05626v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.05626 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 308 words
Related coverage
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
arXiv · Sep 9, 2026
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · Jul 17, 2026
2026.10: You are here 📍
Home Assistant · Oct 7, 2026
Modernizing and scaling support operations with generative AI on AWS
AWS · Sep 2, 2026