Abstract:Human Label Variation (HLV), i.e. systematic differences among annotators' judgments, remains underexplored in benchmarks despite rapid progress in large language model (LLM) development. We address this gap by introducing an evaluation protocol for multimodal large language model (MLLM) benchmarking that explicitly accounts for two conditions: (1) human label agreement and (2) disagreement. We apply this protocol to two state-of-the-art MLLM families (Gemma 3, Qwen 2.5 VL) using non-aggregated human annotations from a social media content classification dataset. Across tasks, we find that larger models tend to perform best on high-agreement subsets, yet often underperform medium-sized models when human disagreement is high, indicating that parameter count alone does not determine sensitivity to ambiguity and subjectivity. These results show that benchmarks based solely on consensus labels can overstate model capabilities in such domains and that incorporating human label variation yields more realistic and robust assessments of MLLMs in content moderation pipelines.
Abstract:This project explores methods to enhance sign language translation of German sign language, specifically focusing on disambiguation of homonyms. Sign language is ambiguous and understudied which is the basis for our experiments. We approach the improvement by training transformer-based models on various bodypart representations to shift the focus on said bodypart. To determine the impact of, e.g., the hand or mouth representations, we experiment with different combinations. The results show that focusing on the mouth increases the performance in small dataset settings while shifting the focus on the hands retrieves better results in larger dataset settings. Our results contribute to better accessibility for non-hearing persons by improving the systems powering digital assistants, enabling a more accurate interaction. The code for this project can be found on GitHub.