@techreport{oai:ipsj.ixsq.nii.ac.jp:00237418,
 author = {Keito, Inoshita and Keito, Inoshita},
 issue = {2},
 month = {Jul},
 note = {The rapid development of AI technology has enabled Large Language Models (LLMs) to acquire extensive general knowledge from vast amounts of text data, making them useful for various tasks. However, it has become evident that LLMs also acquire biases present in their training data, leading to discriminatory behavior towards attributes such as gender, race, and political ideologies. This is particularly concerning in the field of national security, where sentiment recognition bias towards specific countries by LLMs could cause serious problems. Although previous studies have developed datasets for evaluating these biases, several challenges remain in their development methods. This study proposes a novel dataset development method for evaluating sentiment recognition biases of LLMs, based on tweet data related to the Ukraine-Russia war. Specifically, the method involves automated sentiment labeling and anonymization processes using LLMs, aiming to create efficient and high-accuracy datasets. Experimental results confirm that the proposed method effectively evaluates the sentiment recognition biases of LLMs in various conflict structures. In conclusion, this study provides a new method for evaluating biases in LLMs and demonstrates its effectiveness. Future research should focus on developing larger datasets and improving anonymization techniques., The rapid development of AI technology has enabled Large Language Models (LLMs) to acquire extensive general knowledge from vast amounts of text data, making them useful for various tasks. However, it has become evident that LLMs also acquire biases present in their training data, leading to discriminatory behavior towards attributes such as gender, race, and political ideologies. This is particularly concerning in the field of national security, where sentiment recognition bias towards specific countries by LLMs could cause serious problems. Although previous studies have developed datasets for evaluating these biases, several challenges remain in their development methods. This study proposes a novel dataset development method for evaluating sentiment recognition biases of LLMs, based on tweet data related to the Ukraine-Russia war. Specifically, the method involves automated sentiment labeling and anonymization processes using LLMs, aiming to create efficient and high-accuracy datasets. Experimental results confirm that the proposed method effectively evaluates the sentiment recognition biases of LLMs in various conflict structures. In conclusion, this study provides a new method for evaluating biases in LLMs and demonstrates its effectiveness. Future research should focus on developing larger datasets and improving anonymization techniques.},
 title = {A Novel Dataset Development Method for Evaluating Sentiment Recognition Bias of Large Language Models in Conflict Structures},
 year = {2024}
}