| SHAP-based explanation methods: a review for NLP interpretability E Mosca, F Szigeti, S Tragianni, D Gallagher, G Groh Proceedings of the 29th international conference on computational …, 2022 | 101 | 2022 |
| Understanding and interpreting the impact of user context in hate speech detection E Mosca, M Wich, G Groh Proceedings of the Ninth International Workshop on Natural Language …, 2021 | 45 | 2021 |
| " That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks E Mosca, S Agarwal, J Rando-Ramirez, G Groh Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022 | 31 | 2022 |
| Distinguishing Fact from Fiction: A Benchmark Dataset for Identifying Machine-Generated Scientific Papers in the LLM Era. E Mosca, MHI Abdalla, P Basso, M Musumeci, G Groh Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing …, 2023 | 22 | 2023 |
| Detecting word-level adversarial text attacks via shapley additive explanations L Huber, MA Kühn, E Mosca, G Groh Proceedings of the 7th Workshop on Representation Learning for NLP, 156-166, 2022 | 22 | 2022 |
| Accurate cost estimation of memory systems utilizing machine learning and solutions from computer vision for design automation L Servadei, E Mosca, E Zennaro, K Devarajegowda, M Werner, W Ecker, ... IEEE Transactions on Computers 69 (6), 856-867, 2020 | 18 | 2020 |
| Explainable Abusive Language Classification Leveraging User and Network Data M Wich, E Mosca, A Gorniak, J Hingerl, G Groh The European Conference on Machine Learning and Principles and Practice of …, 2021 | 15 | 2021 |
| A benchmark dataset to distinguish human-written and machine-generated scientific papers MHI Abdalla, S Malberg, D Dementieva, E Mosca, G Groh Information 14 (10), 522, 2023 | 14 | 2023 |
| Uncovering trauma in genocide tribunals: An nlp approach using the genocide transcript corpus M Schirmer, IMO Nolasco, E Mosca, S Xu, J Pfeffer Proceedings of the Nineteenth International Conference on Artificial …, 2023 | 9 | 2023 |
| IFAN: An explainability-focused interaction framework for humans and NLP models E Mosca, D Dementieva, TE Ajdari, M Kummeth, K Gringauz, Y Zhou, ... arXiv preprint arXiv:2303.03124, 2023 | 9 | 2023 |
| GrammarSHAP: An efficient model-agnostic and structure-aware NLP explainer E Mosca, D Demirtürk, L Mülln, F Raffagnato, G Groh Proceedings of the First Workshop on Learning with Natural Language …, 2022 | 8 | 2022 |
| “Dr LLM, what do I have?”: The Impact of User Beliefs and Prompt Formulation on Health Diagnoses W Kusa, E Mosca, A Lipani Proceedings of the Third Workshop on NLP for Medical Conversations, 13-19, 2023 | 5 | 2023 |
| Explaining neural NLP models for the joint analysis of Open-and-Closed-Ended survey answers E Mosca, K Harmann, T Eder, G Groh Proceedings of the 2nd workshop on trustworthy natural language processing …, 2022 | 5 | 2022 |
| Explainability of Hate Speech Detection Models E Mosca Technical University of Munich. https://soc.cit.tum.de/persons/edoardo-mosca …, 2020 | 4 | 2020 |
| Combining evolutionary algorithms and deep learning for hardware/software interface optimization L Servadei, E Mosca, M Werner, V Esen, R Wille, W Ecker 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD (MLCAD), 1-6, 2019 | 2 | 2019 |
| FELIX: Automatic and interpretable feature engineering using llms S Malberg, E Mosca, G Groh Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024 | 1 | 2024 |
| A scenario-based approach to the design and use of ethical AI models in managing a health pandemic G Groh, D Brand, JVD Merwe, M Hoffmann, T Eder, E Mosca Munich: Institute for Ethics in Artificial Intelligence, 2021 | 1 | 2021 |
| Cost estimation for configurable model-driven SoC designs using machine learning L Servadei, E Mosca, K Devarajegowda, M Werner, W Ecker, R Wille Proceedings of the 2020 on Great Lakes Symposium on VLSI, 405-410, 2020 | 1 | 2020 |
| 4.3 Study 3: Uncovering Trauma in Genocide Tribunals: An NLP Ap-proach Using the Genocide Transcript Corpus M Schirmer, IMO Nolasco, E Mosca, S Xu, J Pfeffer Natural Language Processing for Violence Studies: Investigating Trauma and …, 2024 | | 2024 |
| Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora? M Anschütz, E Mosca, G Groh arXiv preprint arXiv:2404.06838, 2024 | | 2024 |
Georg GrohAdjunct ProfessorVerificeret mail på in.tum.de