I’m a doctoral student third year from Yokohama National University, with an expected graduation date in March 2025 under the supervision of　Prof. Mori at mori lab. My research interest natural language process. Sepcific in Information Extraction, Prompt and Language Model. Constructed Japanese Information Extraction Mutual Reinforcement Effect Mix Dataset (Incuding Sentence Classification, Text Classification, Sentiment Classification, Sentiment Part-of-Speech Classification, Relation Extraction and Event Extraction). Fine-tuned some Japanese’ PLMs and LLMs. You can find our’s paper codes, models and datasets in Huggingface and github.

Education

Doctor of Informatics (In progress)
April 2022 - March 2025 (Planned)
Graduate School of Environment and Information Sciences, Yokohama National University

Master of Science in Information Technology
April 2020 - March 2022
The Kyoto College of Graduate Studies for Informatics

No Bachelor
October 2014 - December 2018
East China Jiaotong University

September 2014 - 2017
Jiangxi college of construction

Experience

part-timer, National Institute of Informatics Large Language Model Center(2024.5-Persent)

Research part-timer, RIKEN AIP(2024.1-2024.5)

Research Assistant, YNU(2022.10-2023.3)

Publications

(In chronological order. The later the newer)

International Conference

1. Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition, NLDB2023.
   Chengguang Gan, Qinghao Zhang, Tatsunori Mori
2. A Few-Shot Approach to Resume Information Extraction via Prompts, NLDB2023. Chengguang Gan, Tatsunori Mori
3. Sensitivity and Robustness of Large Language Models to Prompt in Japanese. PACLIC37. (2023)Chengguang Gan, Tatsunori Mori
4. Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification. NLDB2024. Chengguang Gan, Qinghao Zhang, Tatsunori Mori

Arxiv

1. Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Tasks. (2023)Chengguang Gan, Qinghao Zhang, Tatsunori Mori
2. USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset. (2023)Chengguang Gan, Qinghao Zhang, Tatsunori Mori
3. GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect. (2023)Chengguang Gan, Qinghao Zhang, Tatsunori Mori
4. MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language Models. (2024)Chengguang Gan, Qingyu Yin, Xinyang He, Hanjun Wei, Yunhao Liang, Younghun Lim, Shijian Wang, Hexiang Huang, Qinghao Zhang, Shiwen Ni, Tatsunori Mori
5. Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt). (2023)Chengguang Gan, Tatsunori Mori

Journal

1. Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening. (Journal of Information Processing, 2024)Chengguang Gan, Qinghao Zhang, Tatsunori Mori

Domestic Conference

1. 英文履歴書データ抽出システムへの BERT 適用性の検討, 2021年度 情報処理学会関西支部 支部大会. 甘程光， 高橋良英
2. Construction of English resume corpus and test with pre-trained language models, 言語処理学会 第29回年次大会. (2023)Chengguang Gan, Tatsunori Mori

Reviewer of COLING, Cogent Engineering