logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Debiasing Large Language Models with Structured Knowledge

delete2025-11-01
delete0
PRE
AI
C
Congda Ma *
T
Tianyu Zhao
M
Manabu Okumura
DOI：10.1587/transinf.2024EDP7326delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Due to biases inherently present in data for pre-training, ifest the same phenomena. Since the bias influences the output from the LLMs across various tasks, the widespread deployment of the LLMs is hampered. We propose a simple method that utilizes structured knowledge to alleviate this issue, aiming to reduce the bias embedded within the LLMs and ensuring they have an encompassing perspective when used in applications. Experimental results indicated that our method has good debiasing ability when applied to existing both autoregressive and masked language models. Additionally, it could ensure that the performances of LLMs on ates the need for training from scratch, thus offering enhanced scalability and cost-effectiveness.
Keywords:
debias
large language model
structured knowledge
low-cost

Journal

I
IEICE Transactions on Information and Systems
IF:
0.8
Papers:
171
Citations:
2.3K

Organization

No organization information available