publications

2026

1. 

   Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs

   Patrick Ahrend, Tobias Eder, Xiyang Yang, and 2 more authors

   arXiv preprint arXiv:2603.05618, 2026

2. 

   Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation

   Nils A Herrmann, Tobias Eder, Jingyi He, and 1 more author

   arXiv preprint arXiv:2603.22985, 2026

2023

1. 

   Retrieving users’ opinions on social media with multimodal aspect-based sentiment analysis

   Miriam Anschütz, Tobias Eder, and Georg Groh

   In 2023 IEEE 17th International Conference on Semantic Computing (ICSC), 2023

2022

1. 

   Bias and comparison framework for abusive language datasets

   Maximilian Wich, Tobias Eder, Hala Al Kuwatly, and 1 more author

   AI and Ethics, 2022

2. 

   Introducing an abusive language classification framework for telegram to investigate the german hater community

   Maximilian Wich, Adrian Gorniak, Tobias Eder, and 3 more authors

   In Proceedings of the International AAAI Conference on Web and Social Media, 2022
3. Mediale Hasssprache und technologische Entscheidbarkeit: Zur ethischen Bedeutung subjektiv-perzeptiver Datenannotationen in der Hate Speech Detection

   Laurence Lerch, Maximilian Wich, Tobias Eder, and 1 more author

   In Medien–Demokratie–Bildung: Normative Vermittlungsprozesse und Diversität in mediatisierten Gesellschaften, 2022

4. 

   Explaining neural NLP models for the joint analysis of open-and-closed-ended survey answers

   Edoardo Mosca, Katharina Harmann, Tobias Eder, and 1 more author

   In Proceedings of the 2nd workshop on trustworthy natural language processing (TrustNLP 2022), 2022

5. 

   Long Input Dialogue Summarization with Sketch Supervision for Summarization of Primetime Television Transcripts

   Nataliia Kees, Thien Nguyen, Tobias Eder, and 1 more author

   In Proceedings of the Workshop on Automatic Summarization for Creative Writing, 2022

6. 

   Comparative analysis of cross-lingual contextualized word embeddings

   Hossain Shaikh Saadi, Viktor Hangya, Tobias Eder, and 1 more author

   In Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL), 2022

2021

1. 

   A scenario-based approach to the design and use of ethical AI models in managing a health pandemic

   Georg Groh, Dirk Brand, JVD Merwe, and 4 more authors

   Munich: Institute for Ethics in Artificial Intelligence, 2021

2. 

   Anchor-based bilingual word embeddings for low-resource languages

   Tobias Eder, Viktor Hangya, and Alexander Fraser

   In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2021

2018

1. Evaluating bilingual word embeddings on the long tail

   Fabienne Braune, Viktor Hangya, Tobias Eder, and 1 more author

   In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018