Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5688-5724
Abstract
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Yipeng Zhang, Haitao Mi, Helen M. Meng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?2024
- Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation2024
- Instruction-tuned Language Models are Better Knowledge Learners2024
- Learning to Edit: Aligning LLMs with Knowledge Editing2024
- SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting2023
- Crawling The Internal Knowledge-Base of Language Models2023
- Toward Self-Learning End-to-End Task-oriented Dialog Systems2022
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Perplexity—a measure of the difficulty of speech recognition tasksThe Journal of the Acoustical Society of America, 1977