6 papers
BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models
Thomas Klassert, Adrian Ulges, Biying Fu
Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image gener…
Agentic Insight Generation in VSM Simulations
Micha Selak, Dirk Krechel, Adrian Ulges +3
Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new ave…
DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
Marcel Lamott, Saifullah Saifullah, Nauman Riaz +11
Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the…
Exploring Generalizable Automated Program Repair with Large Language Models
Viola Campos, Ridwan Shariffdeen, Adrian Ulges +1
Automated Program Repair (APR) proposes bug fixes to aid developers in maintaining software. The state of the art in this domain focuses on LLMs, leveraging their strong capabiliti…
Multicalibration for LLM-based Code Generation
Viola Campos, Robin Kuschnereit, Adrian Ulges
As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likeliho…
Integrating Expert Labels into LLM-based Emission Goal Detection: Example Selection vs Automatic Prompt Design
Marco Wrzalik, Adrian Ulges, Anne Uersfeld +2
We address the detection of emission reduction goals in corporate reports, an important task for monitoring companies' progress in addressing climate change. Specifically, we focus…