CASIA OpenIR  > 复杂系统认知与决策实验室
Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering
Wang, Chenhao1,2; Cao, Pengfei1; Li, Jiachun1,2; Chen, Yubo1,2; Liu, Kang1,2,3; Jiang, Xiaojian4; Xu, Jiexin4; Li, Qiuxia4; Jun Zhao1,2
2024
Conference NameProceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation
Conference Date2024-5
Conference PlaceTorino, Italia
Abstract

Recent work shows large language models can be prompted to generate useful rationales for commonsense question answering (CQA), which can improve the performance of both themselves and other models. However, the cost of deployment and further tuning is relatively expensive for the large models. Some work explores to distill the the rationale-generation ability to convenient small-sized models, yet it typically requires human-authored QA instances during the distillation. In this paper, we propose a novel framework that leverages both knowledge graphs and large language models to synthesize rationale-augmented CQA data. Based on it, we train Leros, a model that can generate helpful rationales to assist generic QA models to accomplish unseen CQA tasks. Empirical results demonstrate Leros can substantially enhance the performance of QA models on five unseen CQA benchmarks, providing better gains than both same-sized counterpart models trained with downstream data and 10x larger language models. Our work reveals a novel way to integrate knowledge from both knowledge graphs and large language models into smaller models. The codes and synthesized resources are publicly available at https://github.com/wchrepo/leros.

Indexed ByEI
Sub direction classification自然语言处理
planning direction of the national heavy laboratory语音语言处理
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56702
Collection复杂系统认知与决策实验室
Corresponding AuthorLiu, Kang
Affiliation1.The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.Shanghai Artificial Intelligence Laboratory
4.China Merchants Bank
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wang, Chenhao,Cao, Pengfei,Li, Jiachun,et al. Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering[C],2024.
Files in This Item: Download All
File Name/Size DocType Version Access License
2024.lrec-main.900.p(909KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Chenhao]'s Articles
[Cao, Pengfei]'s Articles
[Li, Jiachun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Chenhao]'s Articles
[Cao, Pengfei]'s Articles
[Li, Jiachun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Chenhao]'s Articles
[Cao, Pengfei]'s Articles
[Li, Jiachun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2024.lrec-main.900.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.