paper-with-me

Papers

Analyzing Social Biases in Japanese Large Language Models

2024-06-04 · Hitomi Yanaka, Namgi Han, Ryoma Kumon, Jie Lu, Masashi Takeshita, Ryo Sekizawa, Taisei Kato, Hiromi Arai

With the development of Large Language Models (LLMs), social biases in the LLMs have become a crucial issue. While various benchmarks for social biases have been provided across languages, the extent to which Japanese LLMs exhibit social biases has not been fully investigated. In this study, we construct the Japanese Bias Benchmark dataset for Question Answering (JBBQ) based on the English bias benchmark BBQ, and analyze social biases in Japanese LLMs. The results show that while current open Japanese LLMs improve their accuracies on JBBQ by setting larger parameters, their bias scores become larger. In addition, prompts with warnings about social biases and Chain-of-Thought prompting reduce the effect of biases in model outputs, but there is room for improvement in the consistency of reasoning.

📄 PDF Abstract BibTeX arXiv:2406.02050

Code (1)

ynklab/JBBQ_data 공식 구현

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Can Existing Methods Debias Languages Other than English? First Attempt to Analyze and Mitigate Japanese Word Embeddings

2020-12-01 · GeBNLP (COLING) 2020 12 · Masashi Takeshita, Yuki Katsumata, Rafal Rzepka, Kenji Araki

It is known that word embeddings exhibit biases inherited from the corpus, and those biases reflect social stereotypes. Recently, many studies have been conducted to analyze and mitigate biases in word embeddings. Unsupe…

Word Embeddings

Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts

2025-03-03 · Akito Nakanishi, Yukie Sano, Geng Liu, Francesco Pierri

In recent years, Large Language Models have attracted growing interest for their significant potential, though concerns have rapidly emerged regarding unsafe behaviors stemming from inherent stereotypes and biases. Most …

Ethics

JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs

2026-03-21 · Taihei Shiotani, Masahiro Kaneko, Ayana Niwa, Yuki Maruyama 외 arxiv

Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social bias in large languag…

A Japanese Benchmark for Evaluating Social Bias in Reasoning Based on Attribution Theory

2026-04-01 · Taihei Shiotani, Masahiro Kaneko, Naoaki Okazaki arxiv

In enhancing the fairness of Large Language Models (LLMs), evaluating social biases rooted in the cultural contexts of specific linguistic regions is essential. However, most existing Japanese benchmarks heavily rely on …

Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset

2025-09-29 · Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka arxiv

Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previous research has evaluated the impact of b…