Can LLMs learn uncertainty on their own? expressing uncertainty effectively in a self-training...

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Learning from" Silly" Questions Improves Large Language Models, But Only Slightly

T Zhu, S Liu, Y Wang, DF Wong, H Yu… - arxiv preprint arxiv …, 2024 - arxiv.org
Constructing high-quality Supervised Fine-Tuning (SFT) datasets is critical for the training of
large language models (LLMs). Recent studies have shown that using data from a specific …
Speichern Zitieren Ähnliche Artikel Alle 2 Versionen HTML-Version