5 papers · 1 filter
Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation
Claudia Grosser, Maike Heuer, Denis Krompass +1
Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets. However, evaluating federated pre-traini…
The Few-shot Dilemma: Over-prompting Large Language Models
Yongjian Tang, Doruk Tuncel, Christian Koerner +1
Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context…
FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios
Yongjian Tang, Rakebul Hasan, Thomas Runkler
Large Language Models (LLMs) have provided a new pathway for Named Entity Recognition (NER) tasks. Compared with fine-tuning, LLM-powered prompting methods avoid the need for train…
Conceptual In-Context Learning and Chain of Concepts: Solving Complex Conceptual Problems Using Large Language Models
Nishtha N. Vaidya, Thomas Runkler, Thomas Hubauer +2
Science and engineering problems fall in the category of complex conceptual problems that require specific conceptual information (CI) like math/logic -related know-how, process in…
Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering
Cuong Nhat Ha, Shima Asaadi, Sanjeev Kumar Karn +3
Vision-language models, while effective in general domains and showing strong performance in diverse multi-modal applications like visual question-answering (VQA), struggle to main…