OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1434-1445
Abstract
Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling2024
- MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation2022
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models2022
- In-Context Learning for Few-Shot Dialogue State Tracking2022
- Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking2022
- BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression2021
- Zero-shot Generalization in Dialog State Tracking through Generative Question Answering2021
- Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search2021
- Dense Passage Retrieval for Open-Domain Question Answering2020
- FastBERT: a Self-distilling BERT with Adaptive Inference Time2020