Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models
Authors:
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 14999-15008
Abstract
Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis, Ion Androutsopoulos. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- How to measure uncertainty in uncertainty sampling for active learningMachine Learning, 2021
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding2021
- Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems2021
- End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-22020
- Efficient Intent Detection with Dual Sentence Encoders2020
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks2019