PRiSM is proposed, a training-free approach for layer-wise partial fine-tuning that leverages the cosine similarity between pre-trained aggregate token representations across layers to identify inter-layer relationships and achieves competitive performance compared to full fine-tuning.
A. Biswas, Md Fahim, M. Amin et al.· International Conference on...· 0 citations
Large Language Models (LLMs) have achieved remarkable progress across natural language processing (NLP) tasks, yet their capabilities degrade sharply for low-resource languages and dialectally diverse settings. Bangla, the world's sixth most spoken language, exemplifies this gap: existing resources overwhelmingly targe...
M. Jawad, Galib Mahmud Jim, Rafid Ahmed et al.· 0 citations
BanglaMemeX is introduced, a culturally grounded multimodal benchmark comprising 3,000 Bangla memes annotated with multi-dimensional labels and human-written explanations that explicitly describe textual and visual metaphors.
Md Sadman Sakib, Zisan Mahmud, Mohammad Fahim Arefin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.