Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 7467-7509
Abstract
Hengyuan Zhang, Yanru Wu, Dawei Li, Sak Yang, Rui Zhao, Yong Jiang, Fei Tan. Findings of the Association for Computational Linguistics ACL 2024. 2024.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-TuningIEEE Transactions on Audio, Speech and Language Processing, 2025
- Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs2024
- Can LLMs Learn from Previous Mistakes? Investigating LLMs’ Errors to Boost for Reasoning2024
- How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition2024
- LogiQA 2.0—An Improved Dataset for Logical Reasoning in Natural Language UnderstandingIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- Crosslingual Generalization through Multitask Finetuning2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- BERT-Beta: A Proactive Probabilistic Approach to Text Moderation2021
- A Primer in BERTology: What We Know About How BERT WorksTransactions of the Association for Computational Linguistics, 2020
- TNT: Text Normalization based Pre-training of Transformers for Content Moderation2020