تقرير
When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes
العنوان: | When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes |
---|---|
المؤلفون: | Yehudai, Asaf, Bendel, Elron |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Information Retrieval, Computer Science - Machine Learning |
الوصف: | We present FastFit, a method, and a Python package design to provide fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. FastFit utilizes a novel approach integrating batch contrastive learning and token-level similarity score. Compared to existing few-shot learning packages, such as SetFit, Transformers, or few-shot prompting of large language models via API calls, FastFit significantly improves multiclass classification performance in speed and accuracy across FewMany, our newly curated English benchmark, and Multilingual datasets. FastFit demonstrates a 3-20x improvement in training speed, completing training in just a few seconds. The FastFit package is now available on GitHub and PyPi, presenting a user-friendly solution for NLP practitioners. Comment: Accepted to NAACL |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2404.12365 |
رقم الأكسشن: | edsarx.2404.12365 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |