Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Cheap, Consistent, Calibrated, but Biased? Typed Decision Models as Judges
Fabian Lukassen, Christoph Weisser, Alexander Silbersdorff
Typed decision models (TDMs) return a probability for each allowed answer instead of generating text, which makes them candidates for cheaply replacing LLM judges that compare two…
cs.CL2026
CAFE: A Compound-AI Factorial Evaluation Framework
Fabian Lukassen, Christoph Weisser, Thomas Kneib +1
We introduce CAFE (Compound-AI Factorial Evaluation), an open-source platform that brings design of experiments to the evaluation of compound AI systems (CAIS). Such systems expose…
cs.CL2026
Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
Fabian Lukassen, Jan Herrmann, Christoph Weisser +3
Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highly on quality metrics such as…