Jasmin Heierli


2024

pdf bib
Multimodal Conversational Interactions for Facial Composites: A Case for Stateful Prompt Orchestration
Rico Staedeli | Roman Leu | Jasmin Heierli | Max Meisterhans | Elena Gavagnin | Alexandre de Spindler
Proceedings of the 9th edition of the Swiss Text Analytics Conference

pdf bib
Exploring Personalized Learning Support through Retrieval Augmented Generation: A Feasibility Study
Petar Mladenov | Luis Pinheiro | Dino Pelesevic | Jasmin Heierli
Proceedings of the 9th edition of the Swiss Text Analytics Conference

pdf bib
PROMISE: Model-Driven Stateful Prompt Orchestration for Persuasive Conversational Interactions
Wenyuan Wu | Jasmin Heierli | Max Meisterhans | Adrian Moser | Andri Färber | Mateusz Dolata | Elena Gavagnin | Alexandre de Spindler | Gerhard Schwabe
Proceedings of the 9th edition of the Swiss Text Analytics Conference

pdf bib
Bias Bluff Busters at FIGNEWS 2024 Shared Task: Developing Guidelines to Make Bias Conscious
Jasmin Heierli | Silvia Pareti | Serena Pareti | Tatiana Lando
Proceedings of The Second Arabic Natural Language Processing Conference

This paper details our participation in the FIGNEWS-2024 shared task on bias and propaganda annotation in Gaza conflict news. Our objectives were to develop robust guidelines and annotate a substantial dataset to enhance bias detection. We iteratively refined our guidelines and used examples for clarity. Key findings include the challenges in achieving high inter-annotator agreement and the importance of annotator awareness of their own biases. We also explored the integration of ChatGPT as an annotator to support consistency. This paper contributes to the field by providing detailed annotation guidelines, and offering insights into the subjectivity of bias annotation.