@inproceedings{chiang-lee-2024-reasoning,
title = "Over-Reasoning and Redundant Calculation of Large Language Models",
author = "Chiang, Cheng-Han and
Lee, Hung-yi",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-short.15",
pages = "161--169",
abstract = "Large language models (LLMs) can solve problems step-by-step.While this chain-of-thought (CoT) reasoning boosts LLMs{'} performance, it is unclear if LLMs know when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero.GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the questions.We also conduct experiments to explain why LLMs generate redundant calculations and reasonings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiang-lee-2024-reasoning">
<titleInfo>
<title>Over-Reasoning and Redundant Calculation of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng-Han</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) can solve problems step-by-step.While this chain-of-thought (CoT) reasoning boosts LLMs’ performance, it is unclear if LLMs know when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero.GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the questions.We also conduct experiments to explain why LLMs generate redundant calculations and reasonings.</abstract>
<identifier type="citekey">chiang-lee-2024-reasoning</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-short.15</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>161</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Over-Reasoning and Redundant Calculation of Large Language Models
%A Chiang, Cheng-Han
%A Lee, Hung-yi
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F chiang-lee-2024-reasoning
%X Large language models (LLMs) can solve problems step-by-step.While this chain-of-thought (CoT) reasoning boosts LLMs’ performance, it is unclear if LLMs know when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero.GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the questions.We also conduct experiments to explain why LLMs generate redundant calculations and reasonings.
%U https://aclanthology.org/2024.eacl-short.15
%P 161-169
Markdown (Informal)
[Over-Reasoning and Redundant Calculation of Large Language Models](https://aclanthology.org/2024.eacl-short.15) (Chiang & Lee, EACL 2024)
ACL