Scholar
Nils Feldhus
Google Scholar ID: nM50iv8AAAAJ
TU Berlin, BIFOLD, DFKI (Guest)
Natural Language Processing
Interpretability
Explainable AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
433
H-index
13
i10-index
17
Publications
20
Co-authors
17
list available
Publications
20 items
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
2026
Cited
0
Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations
2026
Cited
0
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
2026
Cited
0
Judge Circuits
2026
Cited
0
Simplifying Outcomes of Language Model Component Analyses with ELIA
2026
Cited
0
Persona Prompting as a Lens on LLM Social Reasoning
2026
Cited
0
Order in the Evaluation Court: A Critical Analysis of NLG Evaluation Trends
2026
Cited
0
iFlip: Iterative Feedback-driven Counterfactual Example Refinement
arXiv.org · 2026
Cited
0
Load more
Co-authors
14 total
Sebastian Möller
Professor for Quality and Usability, TU Berlin and Scientific Director, DFKI
Qianli Wang
DFKI & TU Berlin
Vera Schmitt
Head of XplaiNLP Research Group at TU Berlin
Tatiana Anikina
German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus
Gabriele Sarti
PhD Student, University of Groningen
Leonhard Hennig
Senior Researcher, Deutsches Forschungszentrum für Künstliche Intelligenz
Tim Polzehl
German Research Center for Artificial Intelligence
Aljoscha Burchardt
DFKI GmbH, Language Technology Lab
