Welcome! 👋 I am Nils Feldhus and am currently working on my PhD thesis in explainable natural language processing at the German Research Center for Artificial Intelligence and the Technische Universität Berlin under the supervision of Sebastian Möller.
Research interests 👀
My main research interest is making (neural) language models more interpretable by building applications that democratize access to explanations. Topics of interest are rationale generation, data-centric interpretability, information-seeking dialogue, and evaluation measures for generated text.
News 🤩
2024-09-30 | CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems has been accepted to EMNLP 2024 Findings and will be presented by Qianli in Miami, FL, USA. 🗽 His new work Cross-Refine is out on arXiv and currently in submission.
2024-09-08 | Traveling to Japan next week! 🗾 I will first give a talk at Eiji Aramaki’s Social Computing Lab at NAIST (Nara), attend the YRRSDS and SIGDIAL 2024 in Kyoto, and then head to Tokyo for INLG 2024.
2024-07-21 | Paper on sycophancy and political bias evaluation of (German) LLMs accepted to INLG 2024. I will visit Tokyo and present the poster on behalf of Max who I supervised. 🗼
2024-07-12 | First-author paper on instructional explanations in teacher-student dialogues accepted to ACM GoodIT. 🗝
2024-07-02 | Two new co-authored papers: On free-text rationale generation and readability (posted on arXiv) and on feature attribution for multimodal medical decision support (accepted to BioNLP @ ACL 2024).
2024-06-21 | New paper on intent recognition for conversational XAI, CoXQL, posted on arXiv.
2024-06-02 | QoEXplainer accepted to QoMEX and ACM IMX 2024.
2024-04-19 | LLMCheckup accepted to NAACL 2024 HCI+NLP! System demo paper on dialogue-based explainability for video streaming quality of experience in submission.
2024-03-31 | New paper on disinformation detection and the role of explainability accepted to FAccT 2024!
2024-03-23 : Excited to give a talk about Explanation Dialogues at the inaugural BIFOLD Tutorial Day on April 30.
2024-02-28 : Two new papers in submission: A follow-up to InterroLang on the conversational examination of self-explaining LLMs (LLMCheckup) and a resource and evaluation paper on instructional explanations in teacher-student dialogues (ReWIRED).
Education 👨🎓
2021-2025 – Computer Science, PhD, Technische Universität Berlin. Supervised by Sebastian Möller: “Approaches for Generating and Evaluating Natural Language Explanations of Language Models”.
2016-2020 – Cognitive Systems: Language, Learning and Reasoning, MSc, University of Potsdam. Supervised by Manfred Stede: “Utilizing machine translation for bootstrapping abstractive text summarization”.
2013-2016 – Computational Linguistics, BA, Heidelberg University. Supervised by Katja Markert: “An in-depth investigation on timeline summarization evaluation”.
Jobs 👨💼
2020-2025 – Researcher/Software Engineer @ German Research Institute for Artificial Intelligence (DFKI), Berlin, Speech and Language Technology group.
2021-2024: XAINES - Explaining AI with Narratives project, supervised by Sebastian Möller.
2020-2021: European Language Grid project, supervised by Georg Rehm.
2014 – Student assistant at the Institute for Computational Linguistics @ Heidelberg University
Leisure activities and other interests 🎵
Hosting two web radio shows where I mix ambient (Neptunian @ FRISKY Radio, since 2014) and atmospheric electronic music (Idolatry @ Proton Radio, since 2015). I’ve been producing mixes for Mixcloud since 2011. All of these are available on helioscope.net.
Cycling and hiking
Nature photography