Papers by Ulrich Schäfer
On the Effectiveness of Prompt-Moderated LLMs for Math Tutoring at the Tertiary Level (2025.findings-emnlp)
Copied to clipboard
Sebastian Steindl, Fabian Brunner, Nada Sissouno, Dominik Schwagerl, Florian Schöler-Niewiera, Ulrich Schäfer
| Challenge: | Large Language Models (LLMs) have been studied intensively in the context of education, yielding heterogeneous results. |
| Approach: | They conduct a three-phase study with 49 students receiving a review of the topics, solving exercises, and writing an exam. |
| Outcome: | The prompt-moderated LLMs performed better than the unmoderated model . |
CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialogues (2025.coling-main)
Copied to clipboard
| Challenge: | Large-scale Wizard-Of-Oz dialogue datasets lack certain types of utterances, which would make them more realistic. |
| Approach: | They propose to use a large language model to create and repair communication errors in an automatic pipeline. |
| Outcome: | The proposed method is based on linguistic theory and uses a state-of-the-art Large Language Model (LLM) to create the error and repair it. |
MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues (2025.naacl-industry)
Copied to clipboard
| Challenge: | Data scarcity is one of the main problems when it comes to real-world applications of transformer-based models. |
| Approach: | They propose a method to source annotated German monologues from existing monologue material to train TOD systems. |
| Outcome: | The proposed model can be used to train TOD systems on a real-world example of a travel booking service. |
An Improved, Strong Baseline for Pre-Trained Large Language Models as Task-Oriented Dialogue Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that Large Language Models perform insufficiently as TOD systems. |
| Approach: | They propose a self-checking mechanism to improve LLM performance as TOD systems. |
| Outcome: | The proposed model outperforms existing models and improves their performance. |
Detection of Adversarial Prompts with Model Predictive Entropy (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly deployed in high-impact scenarios raising concerns about their safety and security. |
| Approach: | They propose an attack-agnostic pipeline for detecting adversarial inputs without prior knowledge of attack specifications. |
| Outcome: | The proposed pipeline outperforms traditional defenses in terms of adaptability and resource efficiency. |
Counterfactual Dialog Mixing as Data Augmentation for Task-Oriented Dialog Systems (2024.lrec-main)
Copied to clipboard
| Challenge: | High-quality training data for Task-Oriented Dialog systems is costly to come by if no corpora are available. |
| Approach: | They propose a data augmentation technique that generates realistic synthetic dialogs via counterfactuals to increase the amount of training data. |
| Outcome: | The proposed technique achieves state-of-the-art on a benchmark dataset and lower resource setting. |