In The Space

Research and white papers

The are hundreds of smart people focused on issues related to AI trust and safety. The following is just a sample of some of the great work being done.

Model Development

• Jan 2025: Open Problems in Machine Unlearning for AI Safety

• Oct 2024: Language model developers should report train-test overlap

General

• Liquid Foundation Models: Our First Series of Generative AI Models: Could Liquid Foundation Models (LFMs) replace Transformer architecture based models?

• Building Socio-culturally Inclusive Stereotype Resources with Community Engagement

• All that Agrees Is Not Gold: Evaluating Ground Truth Labels and Dialogue Content for Safety

• A Framework to Assess (Dis)agreement Among Diverse Rater Groups

• Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

• AURORA-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

• LLM Agents can Autonomously Hack Websites

• Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

• AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

• An Insider’s Guide to Designing and Operationalizing a Responsible AI Governance Framework

• Evaluating Frontier Models for Dangerous Capabilities

• Frontier Model Forum: What is Red Teaming?

• Holistic Evaluation of Language Models

• THE HISTORY AND RISKS OF REINFORCEMENT LEARNING AND HUMAN FEEDBACK