Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Holtermann, Carolin"'
Autor:
Hinck, Musashi, Holtermann, Carolin, Olson, Matthew Lyle, Schneider, Florian, Yu, Sungduk, Bhiwandiwalla, Anahita, Lauscher, Anne, Tseng, Shaoyen, Lal, Vasudev
We uncover a surprising multilingual bias occurring in a popular class of multimodal vision-language models (VLMs). Including an image in the query to a LLaVA-style VLM significantly increases the likelihood of the model returning an English response
Externí odkaz:
http://arxiv.org/abs/2407.02333
Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of h
Externí odkaz:
http://arxiv.org/abs/2403.03814
The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated modularize
Externí odkaz:
http://arxiv.org/abs/2401.12756
Multi-task learning (MTL) has shown considerable practical benefits, particularly when using language models (LMs). While this is commonly achieved by learning $n$ tasks under a joint optimization procedure, some methods, such as AdapterFusion, divid
Externí odkaz:
http://arxiv.org/abs/2310.01217
Although much work in NLP has focused on measuring and mitigating stereotypical bias in semantic spaces, research addressing bias in computational argumentation is still in its infancy. In this paper, we address this research gap and conduct a thorou
Externí odkaz:
http://arxiv.org/abs/2204.04026