Publications (13)
Immunization against harmful fine-tuning attacks
Domenic Rosati, Jan Wehner, Kai Williams +4
Large Language Models (LLMs) are often trained with safety guards intended to prevent harmful text generation. However, such safety training can be removed by fine-tuning the LLM o…
Agent Benchmarks Fail Public Sector Requirements
Jonathan Rystrøm, Chris Schmitz, Karolina Korgul +2
Deploying Large Language Model-based agents (LLM agents) in the public sector requires assuring that they meet the stringent legal, procedural, and structural requirements of publi…
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou +39
Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstrac…
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Jan Batzner, Sree Harsha Nelaturu, Damian Stachura +45
AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First…
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
Franziska Weeber, Vera Neplenbroek, Jan Batzner +1
Personalization of LLMs by sociodemographic subgroup often improves user experience, but can also introduce or amplify biases and unfair outcomes across groups. Prior work has empl…
Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
Jan Batzner, Volker Stocker, Bingjun Tang +4
Synthetic personae experiments have become a prominent method in Large Language Model alignment research, yet the representativeness and ecological validity of these personae vary…
Bye Bye Perspective API: Lessons for Measurement Infrastructure in NLP, CSS and LLM Evaluation
David Hartmann, Manuel Tonneau, Angelie Kraft +7
The closure of Perspective API at the end of 2026 discards what has functioned as the de facto standard for automated toxicity measurement in NLP, CSS, and LLM evaluation research.…
Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
Jan Batzner, Volker Stocker, Stefan Schmid +1
Sycophantic response patterns in Large Language Models (LLMs) have been increasingly claimed in the literature. We review methodological challenges in measuring LLM sycophancy and…
GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
Jan Batzner, Volker Stocker, Stefan Schmid +1
Large language models (LLMs) are increasingly shaping citizens' information ecosystems. Products incorporating LLMs, such as chatbots and AI Companions, are now widely used for dec…
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
Avijit Ghosh, Anka Reuel, Jenny Chim +45
AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers can…
Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
Anka Reuel, Avijit Ghosh, Jenny Chim +32
Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general c…
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Mubashara Akhtar, Anka Reuel, Prajna Soni +36
Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…
Oversight Structures for Agentic AI in Public-Sector Organizations
Chris Schmitz, Jonathan Rystrøm, Jan Batzner
This paper finds that the introduction of agentic AI systems intensifies existing challenges to traditional public sector oversight mechanisms -- which rely on siloed compliance un…