@inproceedings{wei-etal-2024-guided,
title = "Guided Knowledge Generation with Language Models for Commonsense Reasoning",
author = "Wei, Xiao and
Chen, Haoran and
Yu, Hang and
Fei, Hao and
Liu, Qian",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.61",
pages = "1103--1136",
abstract = "Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs{'} reasoning capabilities, mitigating the influence of inaccurate commonsense knowledge remains a challenge, particularly for small-scale LLMs (e.g., those with less than 10B parameters). In this work, we propose a novel method named Guided Knowledge Generation (GuideKG) to address these issues. It presents three advantages: (i) Employing LLMs to generate knowledge explanations and to automatically assign labels based on the probability of correct answers eliminates the need for costly manual annotation in subsequent training. (ii) Training a new module called the {`}Know-Filter{'}, which is used to evaluate knowledge, and we have introduced a new loss to enhance its performance. (iii) Evaluating the effectiveness of knowledge fragments at the sentence level and fusing them allows for precise control over the generation process of LLMs. We evaluate our GuideKG on small-scale LLMs and show that it outperforms all baselines on four widely-used commonsense reasoning benchmarks. Moreover, our experiments reveal that, with proper guidance, small-scale LLMs can exhibit exceptional performance in commonsense reasoning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2024-guided">
<titleInfo>
<title>Guided Knowledge Generation with Language Models for Commonsense Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs’ reasoning capabilities, mitigating the influence of inaccurate commonsense knowledge remains a challenge, particularly for small-scale LLMs (e.g., those with less than 10B parameters). In this work, we propose a novel method named Guided Knowledge Generation (GuideKG) to address these issues. It presents three advantages: (i) Employing LLMs to generate knowledge explanations and to automatically assign labels based on the probability of correct answers eliminates the need for costly manual annotation in subsequent training. (ii) Training a new module called the ‘Know-Filter’, which is used to evaluate knowledge, and we have introduced a new loss to enhance its performance. (iii) Evaluating the effectiveness of knowledge fragments at the sentence level and fusing them allows for precise control over the generation process of LLMs. We evaluate our GuideKG on small-scale LLMs and show that it outperforms all baselines on four widely-used commonsense reasoning benchmarks. Moreover, our experiments reveal that, with proper guidance, small-scale LLMs can exhibit exceptional performance in commonsense reasoning.</abstract>
<identifier type="citekey">wei-etal-2024-guided</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.61</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1103</start>
<end>1136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guided Knowledge Generation with Language Models for Commonsense Reasoning
%A Wei, Xiao
%A Chen, Haoran
%A Yu, Hang
%A Fei, Hao
%A Liu, Qian
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wei-etal-2024-guided
%X Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs’ reasoning capabilities, mitigating the influence of inaccurate commonsense knowledge remains a challenge, particularly for small-scale LLMs (e.g., those with less than 10B parameters). In this work, we propose a novel method named Guided Knowledge Generation (GuideKG) to address these issues. It presents three advantages: (i) Employing LLMs to generate knowledge explanations and to automatically assign labels based on the probability of correct answers eliminates the need for costly manual annotation in subsequent training. (ii) Training a new module called the ‘Know-Filter’, which is used to evaluate knowledge, and we have introduced a new loss to enhance its performance. (iii) Evaluating the effectiveness of knowledge fragments at the sentence level and fusing them allows for precise control over the generation process of LLMs. We evaluate our GuideKG on small-scale LLMs and show that it outperforms all baselines on four widely-used commonsense reasoning benchmarks. Moreover, our experiments reveal that, with proper guidance, small-scale LLMs can exhibit exceptional performance in commonsense reasoning.
%U https://aclanthology.org/2024.findings-emnlp.61
%P 1103-1136
Markdown (Informal)
[Guided Knowledge Generation with Language Models for Commonsense Reasoning](https://aclanthology.org/2024.findings-emnlp.61) (Wei et al., Findings 2024)
ACL