@inproceedings{wang-etal-2024-leros-learning,
title = "Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering",
author = "Wang, Chenhao and
Cao, Pengfei and
Li, Jiachun and
Chen, Yubo and
Liu, Kang and
Jiang, Xiaojian and
Xu, Jiexin and
Qiuxia, Li and
Zhao, Jun",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.900",
pages = "10303--10315",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-leros-learning">
<titleInfo>
<title>Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiachun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojian</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Qiuxia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">wang-etal-2024-leros-learning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.900</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10303</start>
<end>10315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering
%A Wang, Chenhao
%A Cao, Pengfei
%A Li, Jiachun
%A Chen, Yubo
%A Liu, Kang
%A Jiang, Xiaojian
%A Xu, Jiexin
%A Qiuxia, Li
%A Zhao, Jun
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F wang-etal-2024-leros-learning
%X 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.
%U https://aclanthology.org/2024.lrec-main.900
%P 10303-10315
Markdown (Informal)
[Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering](https://aclanthology.org/2024.lrec-main.900) (Wang et al., LREC-COLING 2024)
ACL
- Chenhao Wang, Pengfei Cao, Jiachun Li, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Li Qiuxia, and Jun Zhao. 2024. Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10303–10315, Torino, Italia. ELRA and ICCL.