JST K Program — Key and Advanced Technology R&D through Cross Community Collaboration

Red Teaming Framework for
Misalignment of Large Language Models

This project builds a security technology foundation for detecting, evaluating, mitigating, and suppressing the misalignment of large language models (behavior that deviates from human expectations and ethics).

News

All news

Overview

Content generated by large language models may contain misalignment such as misinformation, harmful information, discriminatory content, instruction violation, license violation, and leakage of personal information. For models obtained and modified from external sources, evaluating such risks on one's own is not easy.

This project is developing a technology foundation that supports such evaluation, the Red Teaming Framework (RTF). The RTF applies a variety of attacks to a submitted model and evaluates and visualizes its responses from the perspective of misalignment. The evaluation makes use of the evaluation data foundation and adversarial evaluation data foundation that this project builds on its own.

Pages

Project Information

ProgramKey and Advanced Technology R&D through Cross Community Collaboration Program (K Program)
Principal InvestigatorJun Sakuma (Professor, School of Computing, Institute of Science Tokyo)
Research periodFY2024 – FY2029 (planned)
Grant numberJPMJKP24C3
DetailsJST Project Database