@inproceedings{zhang-etal-2024-distillation-explanations,
title = "Distillation with Explanations from Large Language Models",
author = "Zhang, Hanyu and
Wang, Xiting and
Ao, Xiang and
He, Qing",
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.449",
pages = "5018--5028",
abstract = "Free-text explanations are crucial for enhancing the interpretability of AI models. However, training models to generate high-quality free-text explanations is challenging, primarily due to the requirement of a substantial amount of human-written explanations, which can be expensive. Recently, Large language models (LLMs) like ChatGPT and GPT-4 have made remarkable progress in various NLP tasks while also providing explanations alongside their answers. Leveraging LLMs for data labeling offers a more cost-effective alternative. However, a key concern arises from the fact that the answers provided by LLMs are not entirely accurate, potentially introducing noise to both task outputs and explanation generation. To remedy this, we propose a new mechanism, Distillation with Explanations from LLMs. we observe that despite the incorrectness in LLMs-generated answers, their explanations are consistent with their answers. Leveraging this consistency, our method combines the ground truth labels and answers-explanations generated by LLMs, to simultaneously generate more accurate answers and the corresponding free-text explanations. Experimental results demonstrate that our approach achieves improved predictive performance and also generates explanations that exhibit greater alignment with the model{'}s task outputs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-distillation-explanations">
<titleInfo>
<title>Distillation with Explanations from Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiting</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">He</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>Free-text explanations are crucial for enhancing the interpretability of AI models. However, training models to generate high-quality free-text explanations is challenging, primarily due to the requirement of a substantial amount of human-written explanations, which can be expensive. Recently, Large language models (LLMs) like ChatGPT and GPT-4 have made remarkable progress in various NLP tasks while also providing explanations alongside their answers. Leveraging LLMs for data labeling offers a more cost-effective alternative. However, a key concern arises from the fact that the answers provided by LLMs are not entirely accurate, potentially introducing noise to both task outputs and explanation generation. To remedy this, we propose a new mechanism, Distillation with Explanations from LLMs. we observe that despite the incorrectness in LLMs-generated answers, their explanations are consistent with their answers. Leveraging this consistency, our method combines the ground truth labels and answers-explanations generated by LLMs, to simultaneously generate more accurate answers and the corresponding free-text explanations. Experimental results demonstrate that our approach achieves improved predictive performance and also generates explanations that exhibit greater alignment with the model’s task outputs.</abstract>
<identifier type="citekey">zhang-etal-2024-distillation-explanations</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.449</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5018</start>
<end>5028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distillation with Explanations from Large Language Models
%A Zhang, Hanyu
%A Wang, Xiting
%A Ao, Xiang
%A He, Qing
%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 zhang-etal-2024-distillation-explanations
%X Free-text explanations are crucial for enhancing the interpretability of AI models. However, training models to generate high-quality free-text explanations is challenging, primarily due to the requirement of a substantial amount of human-written explanations, which can be expensive. Recently, Large language models (LLMs) like ChatGPT and GPT-4 have made remarkable progress in various NLP tasks while also providing explanations alongside their answers. Leveraging LLMs for data labeling offers a more cost-effective alternative. However, a key concern arises from the fact that the answers provided by LLMs are not entirely accurate, potentially introducing noise to both task outputs and explanation generation. To remedy this, we propose a new mechanism, Distillation with Explanations from LLMs. we observe that despite the incorrectness in LLMs-generated answers, their explanations are consistent with their answers. Leveraging this consistency, our method combines the ground truth labels and answers-explanations generated by LLMs, to simultaneously generate more accurate answers and the corresponding free-text explanations. Experimental results demonstrate that our approach achieves improved predictive performance and also generates explanations that exhibit greater alignment with the model’s task outputs.
%U https://aclanthology.org/2024.lrec-main.449
%P 5018-5028
Markdown (Informal)
[Distillation with Explanations from Large Language Models](https://aclanthology.org/2024.lrec-main.449) (Zhang et al., LREC-COLING 2024)
ACL
- Hanyu Zhang, Xiting Wang, Xiang Ao, and Qing He. 2024. Distillation with Explanations from Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5018–5028, Torino, Italia. ELRA and ICCL.