AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing.

Ji-Ung Lee https://orcid.org/0000-0002-8428-2003

Sarubi Thillainathan Ji-Ung Lee Michael Sullivan Alexander Koller AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing. 2026 March abs/2603.23069 CoRR https://doi.org/10.48550/arXiv.2603.23069 db/journals/corr/corr2603.html#abs-2603-23069 streams/journals/corr

Yifan Wang 0019 Jinyi Mu Mayank Jobanputra Yu Wang Ji-Ung Lee Soyoung Oh Isabel Valera Vera Demberg Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling. 2026 June abs/2606.04284 CoRR https://doi.org/10.48550/arXiv.2606.04284 db/journals/corr/corr2606.html#abs-2606-04284 streams/journals/corr

Zena Al-Khalili Rafi Hakim Dietrich Klakow Ji-Ung Lee Fork-Think with Confidence. 2026 June abs/2606.31484 CoRR https://doi.org/10.48550/arXiv.2606.31484 db/journals/corr/corr2606.html#abs-2606-31484 streams/journals/corr

Yifan Wang 0019 Sukrut Rao Ji-Ung Lee Mayank Jobanputra Vera Demberg B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=c180UH8Dg8 db/journals/tmlr/tmlr2025.html#WangRLJD25 streams/journals/tmlr

Yifan Wang 0019 Sukrut Rao Ji-Ung Lee Mayank Jobanputra Vera Demberg B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability. 2025 February abs/2502.12992 CoRR https://doi.org/10.48550/arXiv.2502.12992 db/journals/corr/corr2502.html#abs-2502-12992 streams/journals/corr

Yifan Wang 0019 Mayank Jobanputra Ji-Ung Lee Soyoung Oh Isabel Valera Vera Demberg Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection? 2025 September abs/2509.22291 CoRR https://doi.org/10.48550/arXiv.2509.22291 db/journals/corr/corr2509.html#abs-2509-22291 streams/journals/corr

Ji-Ung Lee Marc E. Pfetsch Iryna Gurevych Constrained C-Test Generation via Mixed-Integer Programming. 2024 abs/2404.08821 CoRR https://doi.org/10.48550/arXiv.2404.08821 db/journals/corr/corr2404.html#abs-2404-08821

Marcos V. Treviso Ji-Ung Lee Tianchu Ji Betty van Aken Qingqing Cao Manuel R. Ciosici Michael Hassid Kenneth Heafield Sara Hooker Colin Raffel Pedro Henrique Martins André F. T. Martins Jessica Zosa Forde Peter A. Milder Edwin Simpson Noam Slonim Jesse Dodge Emma Strubell Niranjan Balasubramanian Leon Derczynski Iryna Gurevych Roy Schwartz 0001 Efficient Methods for Natural Language Processing: A Survey. 826-860 2023 11 Trans. Assoc. Comput. Linguistics https://doi.org/10.1162/tacl_a_00577 https://www.wikidata.org/entity/Q121298168 db/journals/tacl/tacl11.html#TrevisoLJACCHHH23

Haishuo Fang Ji-Ung Lee Nafise Sadat Moosavi Iryna Gurevych Transformers with Learnable Activation Functions. 2337-2353 2023 EACL (Findings) https://doi.org/10.18653/v1/2023.findings-eacl.181 https://aclanthology.org/2023.findings-eacl.181 conf/eacl/2023f db/conf/eacl/eacl2023f.html#FangLMG23 Jan-Christoph Klie Ji-Ung Lee Kevin Stowe Gözde Gül Sahin Nafise Sadat Moosavi Luke Bates Dominic Petrak Richard Eckart de Castilho Iryna Gurevych Lessons Learned from a Citizen Science Project for Natural Language Processing. 3576-3590 2023 EACL https://doi.org/10.18653/v1/2023.eacl-main.261 https://aclanthology.org/2023.eacl-main.261 conf/eacl/2023 db/conf/eacl/eacl2023.html#KlieLSSMBPCG23

Ulf A. Hamster Ji-Ung Lee Alexander Geyken Iryna Gurevych Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings. 2023 abs/2304.02481 CoRR https://doi.org/10.48550/arXiv.2304.02481 db/journals/corr/corr2304.html#abs-2304-02481

Jan-Christoph Klie Ji-Ung Lee Kevin Stowe Gözde Gül Sahin Nafise Sadat Moosavi Luke Bates Dominic Petrak Richard Eckart de Castilho Iryna Gurevych Lessons Learned from a Citizen Science Project for Natural Language Processing. 2023 abs/2304.12836 CoRR https://doi.org/10.48550/arXiv.2304.12836 db/journals/corr/corr2304.html#abs-2304-12836

Ji-Ung Lee Haritz Puerto Betty van Aken Yuki Arase Jessica Zosa Forde Leon Derczynski Andreas Rücklé Iryna Gurevych Roy Schwartz 0001 Emma Strubell Jesse Dodge Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research. 2023 abs/2306.16900 CoRR https://doi.org/10.48550/arXiv.2306.16900 db/journals/corr/corr2306.html#abs-2306-16900

Ji-Ung Lee Jan-Christoph Klie Iryna Gurevych Annotation Curricula to Implicitly Train Non-Expert Annotators. 343-373 2022 48 Comput. Linguistics 2 https://doi.org/10.1162/coli_a_00436 db/journals/coling/coling48.html#LeeKG22

Ji-Ung Lee Jan-Christoph Klie Iryna Gurevych Erratum: Annotation Curricula to Implicitly Train Non-Expert Annotators. 1141 2022 48 Comput. Linguistics 4 https://doi.org/10.1162/coli_x_00469 db/journals/coling/coling48.html#LeeKG22a

Lorenz Stangier Ji-Ung Lee Yuxi Wang Marvin Müller Nicholas Frick Joachim Metternich Iryna Gurevych TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation. 9-16 2022 AACL/IJCNLP (System Demonstrations) https://doi.org/10.18653/v1/2022.aacl-demo.2 https://aclanthology.org/2022.aacl-demo.2 conf/ijcnlp/2022-d db/conf/ijcnlp/ijcnlp2022-d.html#StangierLWMFMG22

Lorenz Stangier Ji-Ung Lee Yuxi Wang Marvin Müller Nicholas Frick Joachim Metternich Iryna Gurevych TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation. 2022 abs/2208.07846 CoRR https://doi.org/10.48550/arXiv.2208.07846 db/journals/corr/corr2208.html#abs-2208-07846

Haishuo Fang Ji-Ung Lee Nafise Sadat Moosavi Iryna Gurevych Transformers with Learnable Activation Functions. 2022 abs/2208.14111 CoRR https://doi.org/10.48550/arXiv.2208.14111 db/journals/corr/corr2208.html#abs-2208-14111

Marcos V. Treviso Tianchu Ji Ji-Ung Lee Betty van Aken Qingqing Cao Manuel R. Ciosici Michael Hassid Kenneth Heafield Sara Hooker Pedro Henrique Martins André F. T. Martins Peter A. Milder Colin Raffel Edwin Simpson Noam Slonim Niranjan Balasubramanian Leon Derczynski Roy Schwartz 0001 Efficient Methods for Natural Language Processing: A Survey. 2022 abs/2209.00099 CoRR https://doi.org/10.48550/arXiv.2209.00099 db/journals/corr/corr2209.html#abs-2209-00099

Tilman Beck Ji-Ung Lee Christina Viehmann Marcus Maurer Oliver Quiring Iryna Gurevych Investigating label suggestions for opinion mining in German Covid-19 social media. 1-13 2021 ACL/IJCNLP (1) https://doi.org/10.18653/v1/2021.acl-long.1 https://aclanthology.org/2021.acl-long.1 https://www.wikidata.org/entity/Q131458446 conf/acl/2021-1 db/conf/acl/acl2021-1.html#BeckLVMQG20

Tilman Beck Ji-Ung Lee Christina Viehmann Marcus Maurer Oliver Quiring Iryna Gurevych Investigating label suggestions for opinion mining in German Covid-19 social media. 2021 abs/2105.12980 CoRR https://arxiv.org/abs/2105.12980 db/journals/corr/corr2105.html#abs-2105-12980

Ji-Ung Lee Jan-Christoph Klie Iryna Gurevych Annotation Curricula to Implicitly Train Non-Expert Annotators. 2021 abs/2106.02382 CoRR https://arxiv.org/abs/2106.02382 db/journals/corr/corr2106.html#abs-2106-02382

Ji-Ung Lee Christian M. Meyer Iryna Gurevych Empowering Active Learning to Jointly Optimize System and User Demands. 4233-4247 2020 ACL https://doi.org/10.18653/v1/2020.acl-main.390 https://aclanthology.org/2020.acl-main.390/ conf/acl/2020 db/conf/acl/acl2020.html#LeeMG20

Ji-Ung Lee Christian M. Meyer Iryna Gurevych Empowering Active Learning to Jointly Optimize System and User Demands. 2020 abs/2005.04470 CoRR https://arxiv.org/abs/2005.04470 db/journals/corr/corr2005.html#abs-2005-04470

Ji-Ung Lee Erik Schwan Christian M. Meyer Manipulating the Difficulty of C-Tests. 360-370 2019 ACL (1) https://doi.org/10.18653/v1/p19-1035 https://aclanthology.org/P19-1035/ conf/acl/2019-1 db/conf/acl/acl2019-1.html#LeeSM19 Steffen Eger Gözde Gül Sahin Andreas Rücklé Ji-Ung Lee Claudia Schulz 0001 Mohsen Mesgar Krishnkant Swarnkar Edwin Simpson Iryna Gurevych Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems. 1634-1647 2019 NAACL-HLT (1) https://doi.org/10.18653/v1/n19-1165 https://aclanthology.org/N19-1165/ conf/naacl/2019-1 db/conf/naacl/naacl2019-1.html#EgerSRL0MSSG19

Steffen Eger Gözde Gül Sahin Andreas Rücklé Ji-Ung Lee Claudia Schulz 0001 Mohsen Mesgar Krishnkant Swarnkar Edwin Simpson Iryna Gurevych Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems. 2019 abs/1903.11508 CoRR http://arxiv.org/abs/1903.11508 db/journals/corr/corr1903.html#abs-1903-11508

Ji-Ung Lee Erik Schwan Christian M. Meyer Manipulating the Difficulty of C-Tests. 2019 abs/1906.06905 CoRR http://arxiv.org/abs/1906.06905 db/journals/corr/corr1906.html#abs-1906-06905

Betty van Aken Zena Al-Khalili Yuki Arase Niranjan Balasubramanian Luke Bates Tilman Beck Qingqing Cao Richard Eckart de Castilho Manuel R. Ciosici Vera Demberg Leon Derczynski Jesse Dodge Steffen Eger Haishuo Fang Jessica Zosa Forde Nicholas Frick Alexander Geyken Iryna Gurevych Rafi Hakim Ulf A. Hamster Michael Hassid Kenneth Heafield Sara Hooker Tianchu Ji Mayank Jobanputra Dietrich Klakow Jan-Christoph Klie Alexander Koller André F. T. Martins Pedro Henrique Martins Marcus Maurer Mohsen Mesgar Joachim Metternich Christian M. Meyer Peter A. Milder Nafise Sadat Moosavi Jinyi Mu Marvin Müller Soyoung Oh Dominic Petrak Marc E. Pfetsch Haritz Puerto Oliver Quiring Colin Raffel Sukrut Rao Andreas Rücklé Gözde Gül Sahin Claudia Schulz 0001 Erik Schwan Roy Schwartz 0001 Edwin Simpson Noam Slonim Lorenz Stangier Kevin Stowe Emma Strubell Michael Sullivan Krishnkant Swarnkar Sarubi Thillainathan Marcos V. Treviso Isabel Valera Christina Viehmann Yifan Wang 0019 Yu Wang Yuxi Wang