| | Bias in, Bias out: Annotation Bias in Multilingual Large Language Models
Xia Cui, Ziyi Huang and Naeemeh Adel |
| | Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
Vivek Hruday Kavuri, Vysishtya Karanam Karanam, Venkamsetty Venkata Jahnavi, Kriti Madumadukala, Balaji Lakshmipathi Darur and Ponnurangam Kumaraguru |
| | AnthroSet: a Challenge Dataset for Anthropomorphic Language Detection
Dorielle Lonke, Jelke Bloem and Pia Sommerauer |
| | FLARE: An Error Analysis Framework for Diagnosing LLM Classification Failures
Keerthana Madhavan, Luiza Antonie and Stacey Scott |
| | BuST: A Siamese Transformer Model for AI Text Detection in Bulgarian
Andrii Maslo and Silvia Gargova |
| | F*ck Around and Find Out: Quasi-Malicious Interactions with LLMs as a Site of Situated Learning
Sarah ONeill |
| | <think> So let’s replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
Sergey Pletenev, Alexander Panchenko and Daniil Moskovskiy |
| | Anthropomorphizing AI: A Multi-Label Analysis of Public Discourse on Social Media
Muhammad Owais Raza and Areej Fatemah Meghji |
| | Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
Jonathan Hvithamar Rystrøm, Hannah Rose Kirk and Scott Hale |
| | Learn, Achieve, Predict, Propose, Forget, Suffer: Analysing and Classifying Anthropomorphisms of LLMs
Matthew Shardlow, Ashley Williams, Charlie Roadhouse, Filippos Karolos Ventirozos and Piotr Przybyła |
| | Leveraging the Scala type system for secure LLM-generated code
Alexander Sternfeld, Ljiljana Dolamic and Andrei Kucharavy |