🧑‍🔬 Jun Sakuma

🏛️ Affiliations

🎓University of TsukubaTsukuba · Japan2009–2026 · 122 paperscurrent🔬RIKEN Center for Advanced Intelligence ProjectTokyo · Japan2017–2026 · 83 paperscurrent🔬RIKENWako · Japan2017–2026 · 43 paperscurrent🎓Institute of Science TokyoTokyo · Japan2023–2026 · 21 papersEmployment since 2023 · Professorcurrent🎓Nagoya UniversityNagoya · Japan2025–2026 · 2 paperscurrent🏛️Japan Science and Technology AgencyTokyo · Japan2011–2019 · 58 papers🎓Tokyo Institute of TechnologyTokyo · Japan2000–2024 · 51 papersEducation🎓Nagoya Institute of TechnologyNagoya · Japan2016–2019 · 16 papers🎓Kyoto UniversityKyoto · Japan2005–2006 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG) (2026 · 2 citations)
   Retrieval-Augmented Generation (RAG) systems built on sensitive databases can leak private details, such as patient names, to attackers and even to ordinary users.
2. Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models (2026)
   Multi-turn jailbreaks gradually steer a chatbot past its safety guardrails over several conversational exchanges.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Rewriting Pre-Training Data Boosts LLM Performance in Math and Code ↗arXiv:2505.02881 · no summary yetKazuki Fujii et al.2025 · 15 citations
2. Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)Findings of the Association for Computational LinguisticsJunki Mori, Kazuya Kakizaki, Taiki Miyagawa, et al.2026 · 2 citations
3. Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language ModelsFindings of the Association for Computational LinguisticsRagib Amin Nihal, Rui Wen, Kazuhiro Nakadai, et al.2026

🤝 Co-authors here

1 co-author with a page, the most papers together first.

• Rui Wen

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2

🔗 Cited by

Papers of our library cite their works 16 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jun-sakuma/