Skip to content
LLM-jp
NEWS
Release
Resources
Blog
Members
Meeting
CONTACT
NEWS
Release
Resources
Blog
Members
Meeting
CONTACT
JA
EN
LLM-jp
HOME
-
Resources
Resources
Documents / Slides
We also publish an “
Overview of Japanese LLMs
” on GitHub. Click below to learn more.
Open on GitHub
Search
Working Group / Talks & Reports
Academic Domain WG
Corpus Construction WG
Dialogue WG
Evaluation and Tuning WG
Evaluation and Turning WG
Mechanistic Understanding WG
Model Building WG
Multi-modal WG
Principal Elucidation WG
Real-world Interaction WG
Safety WG
Talks and Reports
すべて
Session
27th（2026-3-17）
28th（2026-4-21）
26th (2026-2-24)
25th (2026-1-13)
24th (2025-10-28)
23rd (2025-9-30)
22nd (2025-8-26)
21st (2025-7-22)
20th (2025-6-24)
19th (2025-5-27)
18th (2025-4-22)
17th (2025-3-25)
16th (2025-2-25)
15th (2025-1-14)
14th (2024-11-26)
13th (2024-10-29)
12th (2024-8-27)
11th (2024-7-30)
10th (2024-6-25)
9th (2024-5-28)
8th (2024-3-26)
7th (2024-1-22)
6th (2023-11-29)
5th (2023-10-18)
4th (2023-9-4)
3rd (2023-7-20)
2nd (2023-6-19)
1st (2023-5-15)
すべて
List of Public Resources
LLM-jp Status Report
Kurohashi
Research and Development of an Open Japanese Medical LLM
Kobayashi
Japanese LLM-as-a-Judge Evaluation Tool ‘llm-jp-judge’ Update and Analysis
Nakayama
Corpus Construction WG
Kawahara
Real-world Interaction WG
Ogata
Safety WG
Sekine
LLM-jp Status Report
Kurohashi
Crawling the Japanese Web
Tamura/ROIS
Stockmark-2-VL-100B: A Japanese-Specialized Visual Language Model with Chain-of-Thought Reasoning for Document Reading Comprehension
Shi Chen/Stockmark
The Insight We Gained from the Development of Llama 3.1 Future Code Ja
Ryo Fujii/Future
Dialogue WG
Higashinaka
Multi-modal WG
Okazaki
Evaluation and Tuning WG
Miyao
Corpus Construction WG
Kawahara
Safety WG
Sekine
Safety WG
Sekine
Safety WG
Sekine
Model Building WG
Suzuki
Real-world Interaction WG
Ogata
LLM-jp Status Report
Kurohashi
Evaluating the Faithfulness and Readability of RL-Tuned LLMs
Chaoran Liu
The First Workshop on Fine-Tuning and Evaluating LLMs: A Report
Namgi Han/UT|Katsumata/Retrieva|Miyao|Kiyomaru
SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
Deguchi/NTT
Model Building WG
Suzuki
Evaluation and Tuning WG
Miyao
Dialogue WG
Higashinaka
Real-world Interaction WG
Ogata
Safety WG
Sekine
Corpus Construction WG
Kawahara
Multi-modal WG
Okazaki
Real-world Interaction WG
Ogata
Evaluation and Tuning WG
Miyao
The Role of LLM in Juris-informatics and a Survey of Legal Control over LLM
Ken Sato
Mid-training for LLM
Kodama
Dialogue WG
Higashinaka
Model Building WG
Suzuki
Multi-modal WG
Okazaki
Safety WG
Sekine
Corpus Construction WG
Kawahara
LLM-jp Status Report
Kurohashi
Harnessing AI Agents for Real-World Applications
Kwasi Ankomah / SambaNova
llm-jp-eval-mm: An Evaluation Framework for Evaluating Japanese-centric Vision and Language Model
Sugiura
Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation
Sugiura
A Study on Fine-tuning Methods for Balancing Usefulness and Safety in Japanese Large Language Models
Katsumata
Large-Scale Human Evaluation of LLMs for Japanese
Inoue
Comparative Analysis of the Geospatial Representations in Large Language Models across Models and Languages
Otake
A Comprehensive Study on Supervised Fine-tuning in Large Language Models
Harada
How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders
Inaba
Integrated Framework for LLM Domain Adaptation Based on Synthetic Data
Ogawa
Understanding the Role of Persona and Internal Mechanisms in Large Language Models
Ozaki
Detection of Sensitive Personal Information in the Pre-training Corpus for Large Language Models
Minamoto
llm-jp-judge: Japanese LLM-as-a-Judge Evaluation Tool
Kodama
A Comprehensive Analysis of Memorization in Large Language Models
Kiyomaru
Analyzing the Pretraining of Japanese Large Language Models
Nishida
Development of Prompt Attack Data Collection Application for LLMs and Analysis of Collected Data Characteristics
Hayashi
Introduction of Open Japanese LLM Leaderboard and Statistical Analysis on Evaluation Results
Namgi Han
Developing a Dataset of Misinformation from Social Media and an Accuracy Benchmark for Large Language Models
Nakazato
Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?
Furuhashi
AnswerCarefully: A Dataset for Promoting Safety of Japanese LLMs
Suzuki
LLM-jp Status Report (Oral Report Only)
Kurohashi
Large-Scale Human Evaluation of LLM Safety
Takahashi
Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
Nakamura
LLM-jp-3 VILA: Construction of Japanese Multimodal Data and Powerful Japanese Multimodal Model
Sasagawa
LLM-jp Status Report (Oral Report Only)
Kurohashi
Real-world Interaction WG
Ogata
Safety WG
Sekine
Safety WG
Sekine
Model Building WG
Suzuki
Multi-modal WG
Maeda|Okazaki
Corpus Construction WG
Kawahara
Evaluation and Tuning WG
Miyao
Dataflow Architecture Achieving 198 Tokens per Second with DeepSeek R1 671B
Kenichi Hayashi/SambaNova Systems
PLaMo 2 Tokenizer: Keys to Token Efficiency
Kentaro Imajo/Preferred Networks
Training Progress of LLM-jp-3 Models: Analysis on Downstream Performance
Oda|Nishida
LLM-jp Status Report
Kurohashi
Model Building WG
Suzuki
Multi-modal WG
Okazaki
Evaluation and Tuning WG
Miyao
Real-world Interaction WG
Ogata
Corpus Construction WG
Kawahara
Development of Large-Scale Multimodal Models in Cardiovascular Medicine (ECG/X-ray)
Junichiro Takahashi/UT
Development of X-ray Reading Report Generation Model
Kaito Baba/UT
Efforts to Efficiently Create High-Quality LLM Datasets
Yujiro Terazawa/APTO
LLM Training Using Synthetic Data
Kiyomaru
LLM-jp Status Report (Oral Report Only)
Kurohashi
Development and Evaluation of Tanuki
Kan Hatakeyama/Institute of Science Tokyo
EMNLP2024 Report
Takagi
EMNLP2024 Report
Kodama
EMNLP2024 Report
Liu
Safety WG
Sekine
Corpus Construction WG
Kawahara
Evaluation and Tuning WG
Miyao
Real-world Interaction WG
Ogata
Model Building WG
Suzuki
Multi-modal WG
Okazaki
Discussion on the Training Progress of LLM-jp-3 172B
Oda
LLM-jp Status Report
Kurohashi
BritLLM: Organising, producing, and publishing the first British Large Language Model
Pontus Stenetorp/NII
Pre-training and Post-training of PLaMo100B
Hiroaki Mikami|Kosuke Nakago/Preferred Elements
Multi-modal WG
Maeda|Okazaki|Sugiura|Sasagawa
Page
1
Page
2
Page
3
NEWS
Release
Resources
Blog
Members
Meeting
CONTACT
NEWS
Release
Resources
Blog
Members
Meeting
CONTACT
X-twitter
Github
Youtube
JA
EN
