2 citations · 4 across the 16 of their papers we have counts for
7 papers · 1 filter
VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric
Subhadeep Roy, Christoph Leiter, Steffen Eger
Current image-text evaluation often relies on a global score, which gives limited insight into which semantic details are supported by the image. Explainable metrics provide ration…
Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement
Yiqi Liu, Flavjo Tomori, Nafise Sadat Moosavi +2
Feedback presentation shapes how LLMs use evaluator judgments during translation refinement. We introduce a machine translation protocol that keeps the evaluator score, main issue,…
EdiTikZ: Scientific Figure Editing from Revision Trajectories
Christian Greisinger, Zhixue Zhao, Steffen Eger
Vision-language models (VLMs) have shown strong performance in generating scientific figures from text or images. However, publication-ready figures often require iterative refinem…
When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era
Lotta Kiefer, Brisca Balthes, Christoph Leiter +3
Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this assumption…
TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning
Christian Greisinger, Steffen Eger
Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, ofte…
GerAV: Towards New Heights in German Authorship Verification using Fine-Tuned LLMs on a New Benchmark
Lotta Kiefer, Christoph Leiter, Sotaro Takeshita +2
Authorship verification (AV) is the task of determining whether two texts were written by the same author and has been studied extensively, predominantly for English data. In contr…
Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics
Subhadeep Roy, Gagan Bhatia, Steffen Eger
Automatic metrics are widely used to evaluate text-to-image models, often replacing human judgment in benchmarking, model selection, and large-scale data filtering. Yet they may re…