Sources
Rohan Paul
LLMs can smartly pick their own parameters based on what you ask them to do Dynamic pruning lets LLMs select task-specific parameters on-the-fly, improving efficiency while maintaining performance compared to larger models. ----- 🤔 Original Problem: → Current LLM pruning… https://t.co/zGDPXKvoBf
wtllm_mag Can LLMs handle unknown situations? Francois Cholet speaks about reasoning 👇 Why is this important? Well, when you think about AGI - Intelligent systems that can handle all human tasks - this is where we need to be. Can they adapt to novelty? https://t.co/Nch9A94oJH
- Rohan Paul
LLMs now know when to stick to their guns and when to change their mind AFICE framework helps LLMs maintain their correct stance against opposing arguments while admitting mistakes when wrong, using confidence estimation and preference optimization. ----- 🤔 Original Problem:… https://t.co/IY9TJtwQcq
Additional media
