تقرير
Uncertainty quantification in fine-tuned LLMs using LoRA ensembles
العنوان: | Uncertainty quantification in fine-tuned LLMs using LoRA ensembles |
---|---|
المؤلفون: | Balabanov, Oleksandr, Linander, Hampus |
سنة النشر: | 2024 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Statistics - Machine Learning |
الوصف: | Fine-tuning large language models can improve task specific performance, although a general understanding of what the fine-tuned model has learned, forgotten and how to trust its predictions is still missing. We derive principled uncertainty quantification for fine-tuned LLMs with posterior approximations using computationally efficient low-rank adaptation ensembles. We analyze three common multiple-choice datasets using low-rank adaptation ensembles based on Mistral-7b, and draw quantitative and qualitative conclusions on their perceived complexity and model efficacy on the different target domains during and after fine-tuning. In particular, backed by the numerical experiments, we hypothesise about signals from entropic uncertainty measures for data domains that are inherently difficult for a given architecture to learn. Comment: 8 pages, 4 figures |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2402.12264 |
رقم الأكسشن: | edsarx.2402.12264 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |