Enhancing Task Performance in Continual Instruction Fine-tuning Through Format Uniformity

Author:

Tan Xiaoyu1ORCID,Cheng Leijun2ORCID,Qiu Xihe2ORCID,Shi Shaojie2ORCID,Cheng Yuan3ORCID,Chu Wei1ORCID,Xu Yinghui3ORCID,Qi Yuan3ORCID

Affiliation:

1. INF Technology (Shanghai) Co., Ltd., Shanghai, China

2. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China

3. AI3 Institute, Fudan University, Shanghai, China

Funder

Shanghai Municipal Natural Science Foundation

National Natural Science Foundation of China

Publisher

ACM

Reference42 articles.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023).

2. Giovanni S Alberti, Ernesto De Vito, Matti Lassas, Luca Ratti, and Matteo Santacesaria. 2021. Learning the optimal Tikhonov regularizer for inverse problems. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J.Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 25205--25216. https://proceedings.neurips.cc/paper_files/paper/2021/file/ d3e6cd9f66f2c1d3840ade4161cf7406-Paper.pdf

3. Teodoro Baldazzi Luigi Bellomarini Stefano Ceri Andrea Colombo Andrea Gentili and Emanuel Sallinger. 2023. Fine-Tuning Large Enterprise Language Models via Ontological Reasoning. In Rules and Reasoning Anna Fensel Ana Ozaki Dumitru Roman and Ahmet Soylu (Eds.). Springer Nature Switzerland Cham 86--94.

4. Chris M Bishop. 1995. Training with noise is equivalent to Tikhonov regularization. Neural computation 7, 1 (1995), 108--116.

5. Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3