@inproceedings{yugeswardeenoo-etal-2024-question,
title = "Question-Analysis Prompting Improves {LLM} Performance in Reasoning Tasks",
author = "Yugeswardeenoo, Dharunish and
Zhu, Kevin and
O{'}Brien, Sean",
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.45",
pages = "543--554",
abstract = "Although LLMs have the potential to transform many fields, they still underperform humans in reasoning tasks. Existing methods induce the model to produce step-by-step calculations, but this research explores the question: Does making the LLM analyze the question improve its performance? We propose a novel prompting strategy called Question Analysis Prompting (QAP), in which the model is prompted to explain the question in {'}n{'} words before solving. The value of {'}n{'} influences the length of response generated by the model. QAP is evaluated on GPT-3.5 Turbo and GPT-4 Turbo on arithmetic datasets GSM8K, AQuA, and SAT and commonsense dataset StrategyQA. QAP is compared with other state-of-the-art prompts including chain-of-thought (CoT), Plan and Solve Prompting (PS+) and Take A Deep Breath (TADB). QAP outperforms all state-of-the-art prompts on AQuA and SAT datasets on both GPT-3.5 and GPT-4. QAP consistently ranks among the top-2 prompts on 75{\%} of the tests. A key factor of QAP performance can be attributed to response length, where detailed responses are beneficial when answering harder questions, but can negatively affect easy questions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yugeswardeenoo-etal-2024-question">
<titleInfo>
<title>Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dharunish</namePart>
<namePart type="family">Yugeswardeenoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">O’Brien</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>Although LLMs have the potential to transform many fields, they still underperform humans in reasoning tasks. Existing methods induce the model to produce step-by-step calculations, but this research explores the question: Does making the LLM analyze the question improve its performance? We propose a novel prompting strategy called Question Analysis Prompting (QAP), in which the model is prompted to explain the question in ’n’ words before solving. The value of ’n’ influences the length of response generated by the model. QAP is evaluated on GPT-3.5 Turbo and GPT-4 Turbo on arithmetic datasets GSM8K, AQuA, and SAT and commonsense dataset StrategyQA. QAP is compared with other state-of-the-art prompts including chain-of-thought (CoT), Plan and Solve Prompting (PS+) and Take A Deep Breath (TADB). QAP outperforms all state-of-the-art prompts on AQuA and SAT datasets on both GPT-3.5 and GPT-4. QAP consistently ranks among the top-2 prompts on 75% of the tests. A key factor of QAP performance can be attributed to response length, where detailed responses are beneficial when answering harder questions, but can negatively affect easy questions.</abstract>
<identifier type="citekey">yugeswardeenoo-etal-2024-question</identifier>
<location>
<url>https://aclanthology.org/2024.acl-srw.45</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>543</start>
<end>554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks
%A Yugeswardeenoo, Dharunish
%A Zhu, Kevin
%A O’Brien, Sean
%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 yugeswardeenoo-etal-2024-question
%X Although LLMs have the potential to transform many fields, they still underperform humans in reasoning tasks. Existing methods induce the model to produce step-by-step calculations, but this research explores the question: Does making the LLM analyze the question improve its performance? We propose a novel prompting strategy called Question Analysis Prompting (QAP), in which the model is prompted to explain the question in ’n’ words before solving. The value of ’n’ influences the length of response generated by the model. QAP is evaluated on GPT-3.5 Turbo and GPT-4 Turbo on arithmetic datasets GSM8K, AQuA, and SAT and commonsense dataset StrategyQA. QAP is compared with other state-of-the-art prompts including chain-of-thought (CoT), Plan and Solve Prompting (PS+) and Take A Deep Breath (TADB). QAP outperforms all state-of-the-art prompts on AQuA and SAT datasets on both GPT-3.5 and GPT-4. QAP consistently ranks among the top-2 prompts on 75% of the tests. A key factor of QAP performance can be attributed to response length, where detailed responses are beneficial when answering harder questions, but can negatively affect easy questions.
%U https://aclanthology.org/2024.acl-srw.45
%P 543-554
Markdown (Informal)
[Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks](https://aclanthology.org/2024.acl-srw.45) (Yugeswardeenoo et al., ACL 2024)
ACL