10 30 4

Melisa Russak

melisa

melisa-writer

AI & ML interests

I love definitions

Recent Activity

authored a paper 7 days ago

Expect the Unexpected: FailSafe Long Context QA for Finance

updated a model 19 days ago

Writer/colab

published a model 26 days ago

Writer/colab

View all activity

Organizations

melisa's activity

authored a paper 7 days ago

Expect the Unexpected: FailSafe Long Context QA for Finance

Paper • 2502.06329 • Published Feb 10 • 128

updated a model 19 days ago

Writer/colab

Updated 19 days ago • 1

published a model 26 days ago

Writer/colab

Updated 19 days ago • 1

reacted to wassemgtk's post with ❤️ 26 days ago

Post

1864

# GESAL: Real-Time Adaptation for LLMs

We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like meta-llama/Llama-3.2-1B adapt in real time using user feedback. Check out the code and white paper on GitHub!

🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL)

---

## Why GESAL?

Static LLMs struggle to adapt without heavy retraining. GESAL solves this with:
- **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters.
- **Graph Memory**: Stores adaptations in nodes for scalability.
- **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback.

---

## How It Works

Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats.

---

## Try It

Built with Hugging Face’s transformers:

pip install transformers torch numpy
python Adaptive_Learning_(GESAL).py

Needs a Hugging Face token for Llama-3.2-1B.

---

## Results

GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.