STAR: SocioTechnical Approach to Red Teaming Language Models.

AllImages Videos News Maps Shopping Books

STAR: SocioTechnical Approach to Red Teaming Language Models

Jun 17, 2024 · This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models.

Scholarly articles for STAR: SocioTechnical Approach to Red Teaming Language Models.

scholar.google.com › citations

… privacy norm awareness of language models in action
Shao · Cited by 4

Llm defenses are not robust to multi-turn human …
Li · Cited by 18

STAR: SocioTechnical Approach to Red Teaming Language Models

aclanthology.org › 2024.emnlp-main.1200

This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models.

STAR: SocioTechnical Approach to Red Teaming Language Models

arxiv.org › html

Jun 17, 2024 · This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language ...

[PDF] STAR: SocioTechnical Approach to Red Teaming Language Models

aclanthology.org › 2024.emnlp-ma...

Nov 12, 2024 · We introduce a novel, sociotechnical approach to red teaming that leverages the control of procedural guidance and the accuracy of human ...

STAR: SocioTechnical Approach to Red Teaming Language Models

www.researchgate.net › publication › 38...

Jun 17, 2024 · This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language ...

Laura Weidinger - X

x.com › weidingerlaura › status

STAR: SocioTechnical Approach to Red Teaming Language Models. from x.com

Jun 18, 2024 · New paper out! Very excited that we're able to share STAR: SocioTechnical Approach to Red Teaming Language Models.

Human-Computer Interaction on X: "STAR: SocioTechnical Approach to ...

twitter.com › Smartphones › status

Oct 24, 2024 · This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language ...

Instructions for the Red Teaming task. - ResearchGate

www.researchgate.net › figure › Instructi...

This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models.

Laura Weidinger - X.com

x.com › weidingerlaura › status

Jun 18, 2024 · New paper out! Very excited that we're able to share STAR: SocioTechnical Approach to Red Teaming Language Models.

Bernat Guillen Pegueroles | Papers With Code

paperswithcode.com › search › order_by...

This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. Paper · Add ...