Picture for Sadao Kurohashi

Sadao Kurohashi

Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models

Add code
Oct 08, 2025
Viaarxiv icon

BIS Reasoning 1.0: The First Large-Scale Japanese Benchmark for Belief-Inconsistent Syllogistic Reasoning

Add code
Jun 08, 2025
Viaarxiv icon

Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension

Add code
Mar 03, 2025
Viaarxiv icon

Assessing Large Language Models in Agentic Multilingual National Bias

Add code
Feb 25, 2025
Viaarxiv icon

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

Add code
Aug 20, 2024
Figure 1 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 2 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 3 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 4 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Viaarxiv icon

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Add code
Jul 04, 2024
Figure 1 for LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
Figure 2 for LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
Figure 3 for LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
Figure 4 for LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
Viaarxiv icon

MELD-ST: An Emotion-aware Speech Translation Dataset

Add code
May 21, 2024
Viaarxiv icon

J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution

Add code
Mar 28, 2024
Figure 1 for J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Figure 2 for J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Figure 3 for J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Figure 4 for J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Viaarxiv icon

AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA

Add code
Mar 27, 2024
Figure 1 for AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
Figure 2 for AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
Figure 3 for AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
Figure 4 for AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
Viaarxiv icon

Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese

Add code
Mar 06, 2024
Figure 1 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 2 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 3 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 4 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Viaarxiv icon