LLMs for Science
Context
One of the fastest-growing application areas of LLMs is scientific computing, mathematics, and formal reasoning. However, current models still struggle with:
- Mathematical proof generation
- Symbolic reasoning
- Scientific code correctness
- Long-step logical inference
This project introduces students to new scientific benchmarks and explores how existing models can be extended to perform better on STEM-related tasks.
Goal
- Evaluate models on math/science benchmarks
- Develop new evaluation datasets
- Improve reasoning via structured prompting or RL
- Fine-tune models for domain-specific tasks
Requirements
- Programming experience
- Interest in mathematics or scientific computing
- ML/LLM knowledge recommended