5 papers
Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
Ryoma Kumon, Hitomi Yanaka
While language models demonstrate sophisticated syntactic capabilities, the extent to which their internal mechanisms align with cross-constructional principles studied in linguist…
Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1
As large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding is important. However, LLMs exhibit cultural bias…
Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1
Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previou…
Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective
Hitomi Yanaka, Xinqi He, Jie Lu +6
An increasing number of studies have examined the social bias of rapidly developed large language models (LLMs). Although most of these studies have focused on bias occurring in a…
Analyzing the Inner Workings of Transformers in Compositional Generalization
Ryoma Kumon, Hitomi Yanaka
The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess…