12 subscribers
התחל במצב לא מקוון עם האפליקציה Player FM !
Using Role-Playing Scenarios to Identify Bias in LLMs
Manage episode 440240035 series 3018913
Harmful biases in large language models (LLMs) make AI less trustworthy and secure. Auditing for biases can help identify potential solutions and develop better guardrails to make AI safer. In this podcast from the Carnegie Mellon University Software Engineering Institute (SEI), Katie Robinson and Violet Turri, researchers in the SEI’s AI Division, discuss their recent work using role-playing game scenarios to identify biases in LLMs.
410 פרקים
Manage episode 440240035 series 3018913
Harmful biases in large language models (LLMs) make AI less trustworthy and secure. Auditing for biases can help identify potential solutions and develop better guardrails to make AI safer. In this podcast from the Carnegie Mellon University Software Engineering Institute (SEI), Katie Robinson and Violet Turri, researchers in the SEI’s AI Division, discuss their recent work using role-playing game scenarios to identify biases in LLMs.
410 פרקים
כל הפרקים
×

1 The Best and Brightest: 6 Years of Supporting the President’s Cup Cybersecurity Competition 21:40

1 Updating Risk Assessment in the CERT Secure Coding Standard 26:04

1 Delivering Next Generation Cyber Capabilities to the DoD Warfighter 27:16

1 Getting the Most Out of Your Insider Risk Data with IIDES 39:14

1 Grace Lewis Outlines Vision for IEEE Computer Society Presidency 18:14

1 Improving Machine Learning Test and Evaluation with MLTE 29:06

1 DOD Software Modernization: SEI Impact and Innovation 27:12

1 Securing Docker Containers: Techniques, Challenges, and Tools 39:09

1 An Introduction to Software Cost Estimation 22:55

1 Cybersecurity Metrics: Protecting Data and Understanding Threats 27:00

1 3 Key Elements for Designing Secure Systems 36:28

1 Using Role-Playing Scenarios to Identify Bias in LLMs 45:07

1 Best Practices and Lessons Learned in Standing Up an AISIRT 38:29

1 3 API Security Risks (and How to Protect Against Them) 19:28
ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.