Generative AI Weekly Research Highlights | Oct'23 Part 3

Disclaimer: The content in this video is AI-generated and adheres to YouTube's guidelines. Each video undergoes manual review and curation before publishing to ensure accuracy and quality.

Title: The Foundation Model Transparency Index

Link: https://arxiv.org/pdf/2310.12941.pdf

Title: Sociotechnical Safety Evaluation of Generative AI Systems

Link: https://arxiv.org/pdf/2310.11986.pdf

Title: Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Link: https://arxiv.org/pdf/2310.10844.pdf

Title: A Survey on Video Diffusion Models

Link: https://arxiv.org/pdf/2310.10647.pdf

Title: Privacy in Large Language Models: Attacks, Defenses and Future Directions

Link: https://arxiv.org/pdf/2310.10383.pdf

Title: Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity

Link: https://arxiv.org/pdf/2310.07521.pdf

Title: GenAIPABench: A Benchmark for Generative AI-based Privacy Assistants

Link: https://arxiv.org/pdf/2309.05138.pdf

Title: RALLE: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models

Link: https://arxiv.org/pdf/2308.10633.pdf

00:00 Intro

00:22 Foundation Model Transparency Index

00:53 Sociotechnical Safety of Generative AI

01:09 Adversarial Attacks on LLMs

01:30 Video Diffusion Models

01:47 Privacy in LLMs

02:03 Enhancing LLM Factuality

02:22 GenAIPABench: Privacy Policy Assistance

02:42 RALLE Framework for Factual QA

03:07 End

#generativeai,#promptengineering,#largelanguagemodels,#openai,#chatgpt,#gpt4,#ai,#abcp,#prompt