@inproceedings{sun-etal-2024-enhancing-code,
title = "Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of {LLM}s",
author = "Sun, Zhihong and
Lyu, Chen and
Li, Bolun and
Wan, Yao and
Zhang, Hongyu and
Li, Ge and
Jin, Zhi",
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.521",
pages = "5878--5895",
abstract = "Large Language Models (LLMs) have recently made significant advances in code generation through the {`}Chain-of-Thought{'} prompting technique. This technique empowers the model to autonomously devise {``}solution plans{''} to tackle intricate programming challenges, thereby improving its performance in code generation. Nevertheless, smaller models have been struggling to keep up with LLMs in deducing these plans, adversely affecting their code generation capabilities. Given the considerable size and associated deployment costs, along with concerns about data security, many teams opt for deploying smaller models for code generation. Consequently, there arises a compelling need for transferring LLMs{'} code generation reasoning abilities to the smaller models. In this paper, we propose the CodePLAN framework, which aims to transfer LLMs{'} reasoning capabilities to smaller models through distillation. We adopt a multi-task learning approach, jointly undertaking code generation and solution plan generation tasks, to enhance the code generation capabilities of smaller model. To ensure the superior quality of the solution plans, we advocate for the utilization of backward reasoning and plan sampling strategies. Our experiments show that in comparison to the conventional fine-tuning approach, our approach improves the smaller model{'}s code generation performance (measured in pass@1 metric) by over 130{\%} on the challenging APPS benchmark.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2024-enhancing-code">
<titleInfo>
<title>Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bolun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Jin</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>Large Language Models (LLMs) have recently made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique. This technique empowers the model to autonomously devise “solution plans” to tackle intricate programming challenges, thereby improving its performance in code generation. Nevertheless, smaller models have been struggling to keep up with LLMs in deducing these plans, adversely affecting their code generation capabilities. Given the considerable size and associated deployment costs, along with concerns about data security, many teams opt for deploying smaller models for code generation. Consequently, there arises a compelling need for transferring LLMs’ code generation reasoning abilities to the smaller models. In this paper, we propose the CodePLAN framework, which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation. We adopt a multi-task learning approach, jointly undertaking code generation and solution plan generation tasks, to enhance the code generation capabilities of smaller model. To ensure the superior quality of the solution plans, we advocate for the utilization of backward reasoning and plan sampling strategies. Our experiments show that in comparison to the conventional fine-tuning approach, our approach improves the smaller model’s code generation performance (measured in pass@1 metric) by over 130% on the challenging APPS benchmark.</abstract>
<identifier type="citekey">sun-etal-2024-enhancing-code</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.521</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5878</start>
<end>5895</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs
%A Sun, Zhihong
%A Lyu, Chen
%A Li, Bolun
%A Wan, Yao
%A Zhang, Hongyu
%A Li, Ge
%A Jin, Zhi
%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 sun-etal-2024-enhancing-code
%X Large Language Models (LLMs) have recently made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique. This technique empowers the model to autonomously devise “solution plans” to tackle intricate programming challenges, thereby improving its performance in code generation. Nevertheless, smaller models have been struggling to keep up with LLMs in deducing these plans, adversely affecting their code generation capabilities. Given the considerable size and associated deployment costs, along with concerns about data security, many teams opt for deploying smaller models for code generation. Consequently, there arises a compelling need for transferring LLMs’ code generation reasoning abilities to the smaller models. In this paper, we propose the CodePLAN framework, which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation. We adopt a multi-task learning approach, jointly undertaking code generation and solution plan generation tasks, to enhance the code generation capabilities of smaller model. To ensure the superior quality of the solution plans, we advocate for the utilization of backward reasoning and plan sampling strategies. Our experiments show that in comparison to the conventional fine-tuning approach, our approach improves the smaller model’s code generation performance (measured in pass@1 metric) by over 130% on the challenging APPS benchmark.
%U https://aclanthology.org/2024.lrec-main.521
%P 5878-5895
Markdown (Informal)
[Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs](https://aclanthology.org/2024.lrec-main.521) (Sun et al., LREC-COLING 2024)
ACL
- Zhihong Sun, Chen Lyu, Bolun Li, Yao Wan, Hongyu Zhang, Ge Li, and Zhi Jin. 2024. Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5878–5895, Torino, Italia. ELRA and ICCL.