Profile
Dr. Carolin Lawrence
Manager & Chief Research Scientist
NEC Laboratories Europe
Heidelberg, Germany

I am the manager of Human-Centric AI (HAI) and Chief Research Scientist at NEC Labs Europe. My group and I work on Generative AI with a focus on explainability and usability. We apply Large Language Models and AI agent technology in various use cases in the domains of finance and healthcare. We develop novel techniques in the areas of natural language processing and explainable AI, which we publish at conferences such as ACL, EMNLP or AAAI. I’m passionate about making AI systems that are not only smart but also clear and helpful for everyday users.

Before joining NEC Labs, I was a graduate research assistant and PhD student at Heidelberg University. During that time I worked on reinforcement learning from human feedback for sequence-to-sequence tasks, i.e. question-answering and machine translation. It’s exciting to see how the ideas from my work with sequence-to-sequence tasks and learning from human feedback have evolved into nowadays powerful Large Language Models.

News

2025

  • 3 Papers accepted at ACL 2025
  • Senior Area Chair for ACL and NAACL

2024

  • Senior Area Chair for COLING
  • Member of the EACL 2024 Best Paper Award Committee
  • Senior Area Chair for the Interpretability, Interactivity and Analysis of Models for NLP track at NAACL 2024
  • Senior Area Chair for the Interpretability, Interactivity and Analysis of Models for NLP track at ACL 2024

Selected Papers

  • On Synthesizing Data for Context Attribution in Question Answering. Gorjan Radevski, Kiril Gashteovski, Shahbaz Syed, Christopher Malon, Sebastien Nicolas, Chia-Chien Hung, Timo Sztyler, Verena Heußer, Wiem Ben Rim, Masafumi Enomoto, Kunihiro Takeoka, Masafumi Oyamada, Goran Glavaš, Carolin Lawrence. In Proceedings of the the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). (pre-print)

  • MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis. Daniel Rose, Chia-Chien Hung, Marco Lepri, Israa Alqassem, Kiril Gashteovski and Carolin Lawrence. In Proceedings of the the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). (pre-print)

  • Evaluating Language Models as Synthetic Data Generators. Seungone Kim, Juyoung Suk, Xiang Yue, Vijay Viswanathan, Seongyun Lee, Yizhong Wang, Kiril Gashteovski, Carolin Lawrence, Sean Welleck, Graham Neubig. In Proceedings of the the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). (pre-print)

  • Large Language Models Enable Few-Shot Clustering. Vijay Viswanathan, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, Grahama Neubig. In Transactions of the Association for Computational Linguistics, presenting at (NAACL 2024). (pdf)

  • AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents. Luca Gioacchini, Giuseppe Siracusano, Davide Sanvito, Kiril Gashteovski, David Friede, Roberto Bifulco, Carolin Lawrence. In System Demonstrations of North American Chapter of the Association for Computational Linguistics (NAACL 2024). (pdf) (code)

  • Towards Safer Large Language Models (LLMs). Carolin Lawrence, Roberto Bifulco, Kiril Gastheovski, Chia-Chien Hung, Wiem Ben Rim, Ammar Shaker, Masafumi Oyamada, Kunihiko Sadamasa, Masafumi Enomoto, Kunihiro Takeoka. In NEC Technical Journal Vol.17 No.2 June 2024 Special Issue on Revolutionizing Business Practices with Generative AI — Advancing the Societal Adoption of AI with the Support of Generative AI Technologies. (pdf)

  • Outstanding Paper Award Behavioral Testing of Knowledge Graph Embedding Models for Link Prediction. Wiem Ben Rim, Carolin Lawrence, Kiril Gashteovski, Mathias Niepert, Naoaki Okazaki. In Conference on Automated Knowledge Base Construction (AKBC). (pdf)

  • Learning from Human Feedback: Challenges for Real-World Reinforcement Learning in NLP. Julia Kreutzer, Stefan Riezler and Carolin Lawrence. In 5th Workshop on Structured Prediction for NLP (SPNLP), at 59th Annual Meeting of the Association for Computational Linguistics (ACL). (pdf)

  • Attending to Future Tokens for Bidirectional Sequence Generation. Carolin Lawrence, Bhushan Kotnis, Mathias Niepert. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). (pdf)

  • Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback. Carolin Lawrence, Stefan Riezler. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Melbourne, Australia. (pdf)

  • Response-based Learning for Grounded Machine Translation. Stefan Riezler, Patrick Simianer and Carolin Haas / Lawrence. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), Baltimore, MD. (pdf)