Guided Knowledge Generation with Language Models for Commonsense Reasoning

Xiao Wei, Haoran Chen, Hang Yu, Hao Fei, Qian Liu


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.
Anthology ID:
2024.findings-emnlp.61
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1103–1136
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.61
DOI:
Bibkey:
Cite (ACL):
Xiao Wei, Haoran Chen, Hang Yu, Hao Fei, and Qian Liu. 2024. Guided Knowledge Generation with Language Models for Commonsense Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1103–1136, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Guided Knowledge Generation with Language Models for Commonsense Reasoning (Wei et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.61.pdf