4 papers
Quantifying and Predicting Disagreement in Graded Human Ratings
Leixin Zhang, ÃaÄrı Ãöltekin
It is increasingly recognized that human annotators do not always agree, and such disagreement is inherent in many annotation tasks. However, not all instances in a given task elic…
Modeling Human Perspectives with Socio-Demographic Representations
Leixin Zhang, Cagri Coltekin
Humans often hold different perspectives on the same issues. In many NLP tasks, annotation disagreement can reflect valid subjective perspectives. Modeling annotator perspectives a…
ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?
Leixin Zhang, Steffen Eger, Yinjie Cheng +6
Multimodal large language models (LLMs) have demonstrated impressive capabilities in generating high-quality images from textual instructions. However, their performance in generat…
Tübingen-CL at SemEval-2024 Task 1:Ensemble Learning for Semantic Relatedness Estimation
Leixin Zhang, ÃaÄrı Ãöltekin
The paper introduces our system for SemEval-2024 Task 1, which aims to predict the relatedness of sentence pairs. Operating under the hypothesis that semantic relatedness is a broa…