6 citations · 41 across the 52 of their papers we have counts for
13 papers · 1 filter
Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
Tomoki Doi, Masaru Isonuma, Hitomi Yanaka
Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether…
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models
Hirohane Takagi, Gouki Minegishi, Shota Kizawa +2
Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize th…
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…
Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
Koki Ryu, Hitomi Yanaka
Personalizing the outputs of large language models (LLMs) to align with individual user preferences is an active research area. However, previous studies have mainly focused on cla…
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…
Implementing a Logical Inference System for Japanese Comparatives
Yosuke Mikami, Daiki Matsuoka, Hitomi Yanaka
Natural Language Inference (NLI) involving comparatives is challenging because it requires understanding quantities and comparative relations expressed by sentences. While some app…
Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives?
Yosuke Mikami, Daiki Matsuoka, Hitomi Yanaka
Large Language Models (LLMs) perform remarkably well in Natural Language Inference (NLI). However, NLI involving numerical and logical expressions remains challenging. Comparatives…
LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese
Jie Lu, Du Jin, Hitomi Yanaka
Unlike English, which uses distinct forms (e.g., had, has, will have) to mark the perfect aspect across tenses, Chinese and Japanese lack separate grammatical forms for tense withi…
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…
Bridging Perception and Language: A Systematic Benchmark for LVLMs' Understanding of Amodal Completion Reports
Amane Watahiki, Tomoki Doi, Taiga Shinozaki +4
One of the main objectives in developing large vision-language models (LVLMs) is to engineer systems that can assist humans with multimodal tasks, including interpreting descriptio…
Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models
Taiga Someya, Ryo Yoshida, Hitomi Yanaka +1
Recent work has demonstrated that neural language models encode syntactic structures in their internal representations, yet the derivations by which these structures are constructe…
Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?
Taiga Shinozaki, Tomoki Doi, Amane Watahiki +2
Humans are susceptible to optical illusions, which serve as valuable tools for investigating sensory and cognitive processes. Inspired by human vision studies, research has begun e…
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…