@inproceedings{mcdonald-emami-2024-trace,
title = "Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition",
author = "McDonald, Tyler and
Emami, Ali",
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-srw.35",
doi = "10.18653/v1/2024.acl-srw.35",
pages = "397--410",
abstract = "Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from large-scale teacher models (over 8 billion parameters) to small-scale student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113{\%} on GSM8K and 20{\%} on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, small-scale models to eventually serve as both students and teachers, potentially reducing our reliance on large-scale, proprietary models. Our code, featuring data analytics and testing scripts, is provided here: https://github.com/traceofthought/trace-of-thought-prompting/tree/main.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcdonald-emami-2024-trace">
<titleInfo>
<title>Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from large-scale teacher models (over 8 billion parameters) to small-scale student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113% on GSM8K and 20% on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, small-scale models to eventually serve as both students and teachers, potentially reducing our reliance on large-scale, proprietary models. Our code, featuring data analytics and testing scripts, is provided here: https://github.com/traceofthought/trace-of-thought-prompting/tree/main.</abstract>
<identifier type="citekey">mcdonald-emami-2024-trace</identifier>
<identifier type="doi">10.18653/v1/2024.acl-srw.35</identifier>
<location>
<url>https://aclanthology.org/2024.acl-srw.35</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>397</start>
<end>410</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition
%A McDonald, Tyler
%A Emami, Ali
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mcdonald-emami-2024-trace
%X Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from large-scale teacher models (over 8 billion parameters) to small-scale student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113% on GSM8K and 20% on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, small-scale models to eventually serve as both students and teachers, potentially reducing our reliance on large-scale, proprietary models. Our code, featuring data analytics and testing scripts, is provided here: https://github.com/traceofthought/trace-of-thought-prompting/tree/main.
%R 10.18653/v1/2024.acl-srw.35
%U https://aclanthology.org/2024.acl-srw.35
%U https://doi.org/10.18653/v1/2024.acl-srw.35
%P 397-410
Markdown (Informal)
[Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition](https://aclanthology.org/2024.acl-srw.35) (McDonald & Emami, ACL 2024)
ACL