Generative AI Weekly Research Highlights | Feb'24 Part 4

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.

Summary of Research Papers

1. CHAIN-OF-KNOWLEDGE: GROUNDING LARGE LANGUAGE MODELS VIA DYNAMIC KNOWLEDGE ADAPTING OVER HETEROGENEOUS SOURCES https://arxiv.org/pdf/2305.13269.pdf

2. Chain of Logic: Rule-Based Reasoning with Large Language Models https://arxiv.org/pdf/2402.10400.pdf

3. Chain-of-Specificity: An Iteratively Refining Method for Eliciting Knowledge from Large Language Models https://arxiv.org/pdf/2402.15526.pdf

4. The (R)Evolution of Multimodal Large Language Models: A Survey https://arxiv.org/pdf/2402.12451.pdf

5. Safety of Multimodal Large Language Models on Images and Text https://arxiv.org/pdf/2402.00357.pdf

6. Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content https://arxiv.org/pdf/2402.13926.pdf

7. Round Trip Translation Defence against Large Language Model Jailbreaking Attacks https://arxiv.org/pdf/2402.13517.pdf

8. Can AI-Generated Text be Reliably Detected? https://arxiv.org/pdf/2303.11156.pdf

Chapters:

00:00 Intro

00:16 Chain of knowledge

00:38 Chain of Logic

00:57 Chain-of-Specificity

01:17 The (R)Evolution of Multimodal Large Language Models

01:36 Safety of Multimodal Large Language Models on Images and Text

01:53 LLMs are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content

02:08 Round Trip Translation Defence

02:25 Can AI-Generated Text be Reliably Detected?

02:43 End

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