Elamur Research⌕
☰
home / authors / Nils Feldhus

Nils Feldhus

Nils Feldhus has 4 papers in our library, in 2023–2026, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Reasoning; often with Vera Schmitt, Hinrich Schuetze, Qianli Wang.

4 papers in our library · 2023–2026

OpenAlex · ORCID · Wikidata · h-index 9 · 79 works · 230 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 71 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #6807

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🔬German Research Centre for Artificial IntelligenceKaiserslautern · Germany2020–2026 · 32 papersEmployment 2020–2024 · Researcher and Software Engineer, Speech and Language Technology (Berlin)current🎓Technische Universität BerlinBerlin · Germany2021–2026 · 28 papersEmployment 2025–2026 · Postdoctoral Researcher, Quality and Usability Labcurrent🔬Berlin Institute for the Foundations of Learning and DataBerlin · Germany2025–2026 · 11 papersEmployment 2025–2026current🎓University of GroningenGroningen · Netherlands2023–2027 · 4 papersEmployment 2026–2027 · Postdoctoral Researcher, Center for Language and Cognitioncurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 4 worksComputer Science · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksBiochemistry, Genetics and Molecular Biology · 1 workMolecular Biology · 1 workComputer Vision and Pattern Recognition · 1 work

🧭 Topics 5Research subjects and languages the work is about.Interpretability · 1 workEfficient models & compression · 1 workLanguage models & pretraining · 1 workReasoning · 1 workMultilingual & cross-lingual NLP · 1 work

 Works by year

2020s

20263 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Inseq: An Interpretability Toolkit for Sequence Generation Models (2023 · 97 citations)
    Most feature attribution research and tooling in NLP targets classification, where each input token gets a single importance score.
  2. Persona Prompting as a Lens on LLM Social Reasoning (2026 · 2 citations)
    The paper asks whether persona prompting (PP), where an LLM is told to answer as someone with given demographic traits, changes the word-level rationales it gives along with its labels, and whether those simulated viewpoints match real human annotators.
  3. Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall (2026 · 2 citations)
    The paper asks how post-training weight quantization affects factual knowledge recall (FKR), meaning an LLM's ability to retrieve facts stored during pretraining.
  4. Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation (2026)
    Counterfactual explanations are small edits to an input that flip a classifier's prediction. LLMs produce them well in English, but their quality in other languages had not been studied. To examine this, the authors evaluate three open instruction-tuned LLMs on XNLI and SIB200, two multilingual classification…

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. Inseq: An Interpretability Toolkit for Sequence Generation ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Gabriele Sarti, Nils Feldhus, Ludwig Sickert, et al.2023 · 97 citations
  2. German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect ↗Proceedings of the 17th International Natural Language Generation Conference · no summary yetMaximilian Bleick et al.2024 · 5 citations
  3. Evaluating German Transformer Language Models with Syntactic Agreement Tests ↗arXiv:2007.03765 · Proceedings of the 5th Swiss Text Analytics Conference and the 16th Conference on Natural Language Processing, SwissText/KONVENS 2020, Zurich, Switzerland, June 23-25, 2020 [online only]. CEUR Workshop Proceedings 2624 · no summary yetKarolina Zaczynska et al.2020 · 5 citations
  4. Persona Prompting as a Lens on LLM Social ReasoningConference of the European Chapter of the Association for Computational Linguistics (EACL)Jing Yang, Moritz Hechtbauer, Elisabeth Khalilov, et al.2026 · 2 citations
  5. Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge RecallWorkshop on Trustworthy NLPQianli Wang, Mingyang Wang, Nils Feldhus, et al.2026 · 2 citations
  6. Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Qianli Wang, Van Bach Nguyen, Yihong Liu, et al.2026

 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 71 times (of the 149,439 papers whose bibliographies we read); 9 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nils-feldhus/