Generative AI Weekly Research Highlights | Feb'24 Part 2

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.

1. A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications https://arxiv.org/pdf/2402.07927.pdf

2. When Large Language Models Meet Vector Databases: A Survey https://arxiv.org/pdf/2402.01763.pdf

3. DeepInception: Hypnotize Large Language Model to Be Jailbreaker https://arxiv.org/pdf/2311.03191.pdf

4. SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models https://arxiv.org/pdf/2402.05044.pdf

5. Measuring Implicit Bias in Explicitly Unbiased Large Language Models https://arxiv.org/pdf/2402.04105.pdf

6. Organic or Diffused: Can We Distinguish Human Art from AI-generated Images? https://arxiv.org/pdf/2402.03214.pdf

7. Examining Gender and Racial Bias in Large Vision–Language Models Using a Novel Dataset of Parallel Images https://arxiv.org/pdf/2402.05779.pdf

8. Detecting Multimedia Generated by Large AI Models: A Survey https://arxiv.org/pdf/2402.00045.pdf

00:00 Intro

00:21 Mastering Prompt Engineering

00:48 LLMs & Vector Databases: A New Era

01:11 Jailbreaking LLMs with Deep Inception

01:30 Benchmarking AI Safety: The Salad Bench

01:53 Unveiling Implicit Biases in LLMs

02:14 Art Authenticity in the AI Age

02:35 Confronting Bias in Vision Language Models

02:54 Detecting AI-Generated Multimedia

03:22 End

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