SCITUNE: Aligning Large Language Models with Scientific Multimodal Instructions
Kaydedildi:
| Yayımlandı: | arXiv.org (Jul 3, 2023), p. n/a |
|---|---|
| Yazar: | |
| Diğer Yazarlar: | , , |
| Baskı/Yayın Bilgisi: |
Cornell University Library, arXiv.org
|
| Konular: | |
| Online Erişim: | Citation/Abstract Full text outside of ProQuest |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2832891468 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2832891468 | ||
| 045 | 0 | |b d20230703 | |
| 100 | 1 | |a Horawalavithana, Sameera | |
| 245 | 1 | |a SCITUNE: Aligning Large Language Models with Scientific Multimodal Instructions | |
| 260 | |b Cornell University Library, arXiv.org |c Jul 3, 2023 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving the LLMs to align existing foundation models with scientific disciplines, concepts and goals. In this work, we present SciTune as a tuning framework to improve the ability of LLMs to follow scientific multimodal instructions. To test our methodology, we use a human-generated scientific instruction tuning dataset and train a large multimodal model LLaMA-SciTune that connects a vision encoder and LLM for science-focused visual and language understanding. In comparison to the models that are finetuned with machine generated data only, LLaMA-SciTune surpasses human performance on average and in many sub-categories on the ScienceQA benchmark. | |
| 653 | |a Tuning | ||
| 653 | |a Large language models | ||
| 653 | |a Coders | ||
| 653 | |a Human performance | ||
| 700 | 1 | |a Munikoti, Sai | |
| 700 | 1 | |a Stewart, Ian | |
| 700 | 1 | |a Kvinge, Henry | |
| 773 | 0 | |t arXiv.org |g (Jul 3, 2023), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2832891468/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2307.01139 |