54 citations · 126 across the 51 of their papers we have counts for
58 papers
BehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction
Tobias Schneider, Danial Fahrner, Soren Antebi +4
Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-token prediction…
Evaluating and Benchmarking the System One Model Jev
Tobias Deußer, Lorenz Sparrenberg, Rafet Sifa
Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a position on a rubric…
Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation
Tobias Deußer, Abhishek Pillai, Aurelio F. Bariviera +5
Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but verifiable grounding in the au…
On the Impact of Anonymization on the Performance of Large Language Models
Tobias Deußer, Max Hahnbück, Lorenz Sparrenberg +3
As large language models are increasingly deployed in sensitive domains, anonymizing input data to protect personally identifiable information has become a critical practice. Howev…
Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs
Shahzeb Qamar, Lorenz Sparrenberg, Christian Bauckhage +5
Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluating these models is largely b…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg +4
Post-Training Quantization has become widely used to compress large language models to make them deployable on resource-constrained devices. However, the evaluation of quantization…