DiscoverSoftware Engineering Institute (SEI) Podcast SeriesUsing Role-Playing Scenarios to Identify Bias in LLMs
Using Role-Playing Scenarios to Identify Bias in LLMs

Using Role-Playing Scenarios to Identify Bias in LLMs

Update: 2024-09-161
Share

Description

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.

Comments 
Top Podcasts
The Best New Comedy Podcast Right Now – June 2024The Best News Podcast Right Now – June 2024The Best New Business Podcast Right Now – June 2024The Best New Sports Podcast Right Now – June 2024The Best New True Crime Podcast Right Now – June 2024The Best New Joe Rogan Experience Podcast Right Now – June 20The Best New Dan Bongino Show Podcast Right Now – June 20The Best New Mark Levin Podcast – June 2024
In Channel
Securing Docker Containers: Techniques, Challenges, and Tools

Securing Docker Containers: Techniques, Challenges, and Tools

2024-12-1639:09

An Introduction to Software Cost Estimation

An Introduction to Software Cost Estimation

2024-12-0422:55

Cybersecurity Metrics: Protecting Data and Understanding Threats

Cybersecurity Metrics: Protecting Data and Understanding Threats

2024-10-1127:00

3 Key Elements for Designing Secure Systems

3 Key Elements for Designing Secure Systems

2024-10-0236:28

Using Role-Playing Scenarios to Identify Bias in LLMs

Using Role-Playing Scenarios to Identify Bias in LLMs

2024-09-1645:07

Best Practices and Lessons Learned in Standing Up an AISIRT

Best Practices and Lessons Learned in Standing Up an AISIRT

2024-09-0938:29

3 API Security Risks (and How to Protect Against Them)

3 API Security Risks (and How to Protect Against Them)

2024-08-2219:28

Evaluating Large Language Models for Cybersecurity Tasks: Challenges and Best Practices

Evaluating Large Language Models for Cybersecurity Tasks: Challenges and Best Practices

2024-07-2543:05

Capability-based Planning for Early-Stage Software Development

Capability-based Planning for Early-Stage Software Development

2024-07-1833:55

Safeguarding Against Recent Vulnerabilities Related to Rust

Safeguarding Against Recent Vulnerabilities Related to Rust

2024-07-0126:25

Developing a Global Network of Computer Security Incident Response Teams (CSIRTs)

Developing a Global Network of Computer Security Incident Response Teams (CSIRTs)

2024-06-2130:51

Automated Repair of Static Analysis Alerts

Automated Repair of Static Analysis Alerts

2024-05-3127:05

Cyber Career Pathways and Opportunities

Cyber Career Pathways and Opportunities

2024-05-2831:23

My Story in Computing with Sam Procter

My Story in Computing with Sam Procter

2024-04-2437:15

Developing and Using a Software Bill of Materials Framework

Developing and Using a Software Bill of Materials Framework

2024-04-0437:37

The Importance of Diversity in Cybersecurity: Carol Ware

The Importance of Diversity in Cybersecurity: Carol Ware

2024-03-2126:37

The Importance of Diversity in Software Engineering: Suzanne Miller

The Importance of Diversity in Software Engineering: Suzanne Miller

2024-03-2129:02

The Importance of Diversity in Artificial Intelligence: Violet Turri

The Importance of Diversity in Artificial Intelligence: Violet Turri

2024-03-1516:57

Using Large Language Models in the National Security Realm

Using Large Language Models in the National Security Realm

2024-02-1634:45

Atypical Applications of Agile and DevSecOps Principles

Atypical Applications of Agile and DevSecOps Principles

2024-02-0933:41

loading
Google Play
Download from Google Play
Castbox
Download from App Store
usUnited States
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Using Role-Playing Scenarios to Identify Bias in LLMs

Using Role-Playing Scenarios to Identify Bias in LLMs