Aug 3, 2024 10:00 AM

Decoding the Unspoken: Prompting LLMs for Indigenous Languages

Diving into prompting techniques for translations in unseen before languages and the challenges within that space.

Agenda:

👋 Quick Welcome (5 mins) - Kicking off the session with a warm greeting and what to expect.

🧑‍💼 Brief Introduction from Participants (1 min each) - Participants share their name, location, occupation, and one expectation from the call.

🤖 Overview of Self-Evolving LLM-based Agents as a Theme for the Session (5 mins) - Diving into prompting techniques for translations in unseen before languages and the challenges within that space.

📄 Overview of the Papers Discussed (5 mins) - Quick summary of the key papers we'll be exploring:

  •    📑 Paper 1: "Learning-From-Mistakes Prompting for Indigenous Language Translation"
  • https://arxiv.org/abs/2407.13343

🗣️ Introduction by the Community Agent (5 mins) - A brief introduction to the session by the AI agent, setting the stage for the discussions.

Q&A from Research Agent (15 mins) - An interactive Q&A session, with questions prepared by the AI agent to stimulate discussion and deepen understanding.

🎉 After-party (15 mins) - An informal chat to relax, network, and discuss AI, life, and everything in between.

Open-source non-profit research lab
While you are here, join our community!
Evaluate autonomous agents, collaborate on real-world business process challenges, and drive the industry forward with benchmarks
🛠️
🛠️
Evaluate your agent solutions against real world problems, instead of research datasets and fancy demos
💸
💸
We are non-profit but your agents will be most likely sponsored by real world companies that end up utilizing them in their operations
🎯
🎯
Win prizes for solving and automating challenging business processes funded by sponsors
🤝
🤝
Contribute to non-profit 501(c)(3), open-source solution for testing agent applications and support independent ecosystem of tools
Join the Community
Start Here
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.