Chengguang Gan

• 2026GuideWeb accepted to AACL-IJCNLP 2026 Findings on September 8.
• 2026New preprint — GRPO Web Agent: a controlled study of learning-rate-gated failure in small language and vision-language models.
• 2026New preprint — MAG: a benchmark and harness for multimodal action and guide generation.
• 2026MMM accepted to ACL 2026 Findings.
• 2025Joined Techtouch as an LLM Researcher.
• 2025GIELLM at IJCNN 2025; USA at PACLIC 2025; two code-generation papers at ICIC 2025.
• 2025Received my Ph.D. in Informatics from Yokohama National University.
• 2024II-Bench accepted to NeurIPS 2024 (Datasets & Benchmarks Track).

Bold = me. Citation counts via Google Scholar (September 9, 2026).

1. 2026

   How Output Format Confounds Data Quality and Capability in Instruction Tuning

   Chengguang Gan, Hanjun Wei, Yunhao Liang, Qinghao Zhang, Shiwen Ni, Zhixi Cai

   Preprint arXiv
2. 2026

   Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

   Chengguang Gan, Yunhao Liang, Hanjun Wei, Qinghao Zhang, Shiwen Ni

   Preprint arXiv
3. 2026

   Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem

   Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni

   Preprint arXiv
4. 2026

   Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits

   Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni

   Preprintcited by 1 arXiv
5. 2026

   Do Code Language Models Follow Tests? Paired Interventions on Program Behavior

   Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni

   Preprint arXiv
6. 2026

   A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

   Chengguang Gan, Zhixi Cai, Yunhao Liang, Hanjun Wei, Shiwen Ni, Qinghao Zhang

   Preprint arXiv
7. 2026

   MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation

   Chengguang Gan, Hanjun Wei, Yunhao Liang, Zhixi Cai, Qinghao Zhang, Shiwen Ni

   Preprint arXiv
8. 2026

   A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

   Chengguang Gan, Sunbowen Lee, Qingyu Yin, Yunhao Liang, Xinyang He, Hanjun Wei, Younghun Lim, Shijian Wang, Hexiang Huang, QingHao Zhang, Shiwen Ni, Tatsunori Mori

   ACL 2026 Findingscited by 2 ACL Anthology
9. 2026

   GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs

   Chengguang Gan, Yunhao Liang, Yoshihiro Tsujii, Tatsunori Mori, Shiwen Ni, Hiroki Itoh

   AACL-IJCNLP 2026 Findings (Accepted)cited by 2 arXiv
10. 2025

    GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effects

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    IJCNN 2025cited by 17 IEEE
11. 2025

    USA Model: Japanese Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part-of-Speech Dataset

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    PACLIC 2025 ACL Anthology
12. 2025

    RECODE: Leveraging Reliable Self-generated Tests and Fine-Grained Execution Feedback to Enhance LLM-Based Code Generation

    Yunhao Liang, Ruixuan Ying, Takuya Taniguchi, Chengguang Gan, Zhe Cui

    ICIC 2025cited by 8 Springer
13. 2025

    Exploring Behavior-Driven Development for Code Generation

    Yunhao Liang, Chengguang Gan, Ruixuan Ying, Zhe Cui

    ICIC 2025cited by 5 Springer
14. 2025

    Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System

    Lei Zheng, Ning Li, Chengguang Gan, Yong Yu, Weinan Zhang

    APWeb-WAIM 2025cited by 1 Springer
15. 2025

    M-MRE: Extending the Mutual Reinforcement Effect to Multimodal Information Extraction

    Chengguang Gan, Zhixi Cai, Yanbin Wei, Yunhao Liang, Shiwen Ni, Tatsunori Mori

    Preprintcited by 1 arXiv
16. 2025

    Decoding Prokaryotic Whole Genomes with a Product-Contextualized Large Language Model

    Shiwen Ni, Shuaimin Li, Shijian Wang, Wenzhi Xue, Luoxi Zhang, Liyang Fan, Xinping Bi, Yitai Li, Chengguang Gan, Jiarui Jin, Yuan Lu, Ahmadreza Argha, Hamid Alinejad-Rokny, Tong Si, Min Yang, Teng Wang

    bioRxiv bioRxiv
17. 2024

    Application of LLM Agents in Recruitment: A Novel Framework for Automated Resume Screening

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    Journal of Information Processingcited by 173 J-STAGE
18. 2024

    II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models

    Ziqiang Liu, Feiteng Fang, Xi Feng, Xinrun Du, Chenhao Zhang, Zekun Wang, Yuelin Bai, Qixuan Zhao, Liyang Fan, Chengguang Gan, et al.

    NeurIPS 2024cited by 22 Proceedings
19. 2024

    Think from Words (TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    NLDB 2024cited by 1 Springer
20. 2024

    Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt

    Chengguang Gan, Tatsunori Mori

    Preprint arXiv
21. 2024

    Demonstrating Mutual Reinforcement Effect through Information Flow

    Chengguang Gan, Xuzheng He, Qinghao Zhang, Tatsunori Mori

    Preprint arXiv
22. 2023

    Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks

    Chengguang Gan, Tatsunori Mori

    PACLIC 37cited by 53 ACL Anthology
23. 2023

    A Few-Shot Approach to Resume Information Extraction via Prompts

    Chengguang Gan, Tatsunori Mori

    NLDB 2023cited by 18 Springer
24. 2023

    Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    NLDB 2023cited by 12 Springer
25. 2023

    Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Tasks

    Chengguang Gan, Qinghao Zhang, Tatsunori Mori

    Preprint arXiv
26. 2023

    Construction of English Resume Corpus and Test with Pre-trained Language Models

    Chengguang Gan, Tatsunori Mori

    ANLP 2023cited by 10 arXiv
27. 2021

    英文履歴書データ抽出システムへの BERT 適用性の検討

    Chengguang Gan, Yoshihide Takahashi

    IPSJ Kansai 2021 IPSJ

Datasets, models, and code behind the papers — free to use.

More on Hugging Face and GitHub.

When I’m away from the terminal.