Generative AI Weekly Research Highlights | Sep'23 Part 2 | Hallucinations in LLMs, phi -1.5..

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.

A Survey of Hallucination in “Large” Foundation Models [https://arxiv.org/pdf/2309.05922.pdf]

The Rise and Potential of Large Language Model Based Agents: A Survey [https://arxiv.org/pdf/2309.07864v1.pdf]

Demystifying Practices, Challenges and Expected Features of Using GitHub Copilot [https://arxiv.org/pdf/2309.05687.pdf]

Textbooks Are All You Need II: phi-1.5 technical report [https://arxiv.org/pdf/2309.05463.pdf]

RAIN: Your Language Models Can Align Themselves without Finetuning [https://arxiv.org/pdf/2309.07124.pdf]

TREE OF UNCERTAIN THOUGHTS REASONING FOR LARGE LANGUAGE MODELS [https://arxiv.org/pdf/2309.07694.pdf]

TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models [https://arxiv.org/pdf/2309.06719.pdf]

SwitchGPT: Adapting Large Language Models for Non-Text Outputs [https://arxiv.org/pdf/2309.07623.pdf]

00:00 Intro

00:17 Survey of Hallucinations in Foundation Models

00:39 LLM-Based Agents and Their Potentials

00:58 GitHub Co-pilot in Practice

01:17 Efficacy of Smaller Transformer Models

01:37 RAIN: Aligning LLMs with Human Preferences

01:54 Enhancing LLM Reasoning with Uncertainty

02:09 Traffic GPT for Urban Traffic Management

02:29 Switch GPT: Adapting LLMs for Non-Text Outputs

02:53 End

#generativeai,#promptengineering,#largelanguagemodels,#openai,