Tutorial Reading Group 2024 #4

The 4th tutorial reading group 2024 will be held on 30th May 2024, Thursday 13:00-16:00 online via Teams. Mr. Jinwei Hu will give us a talk on “How to Control LLMs’ behaviors and Design Strategy to safeguard LLMs”.

Teams Link

Meeting ID: 386 776 521 756

Passcode: jnZAom

Reference:

• [1] Finetuned Language Models Are Zero-Shot Learners
• [2] Training language models to follow instructions with human feedback
• [3] Constitutional ai: Harmlessness from ai feedback
• [4] Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• [5] NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
• [6] Prompting Is Programming: A Query Language for Large Language Models
• [7] RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
• [8] A Causal Explainable Guardrails for Large Language Models
• [9] Safeguarding Large Language Models: A Survey

Related Codes:

• [1] Llama Guard

• [2] NeMo

• [3] Trulens

• [4] Lmql

Slides:

• Slides is available here!