Improving LLM Math Reasoning with Prompting and RAG by Liu ChangImproving LLM Math Reasoning with Prompting and RAG by Liu Chang

Improving LLM Math Reasoning with Prompting and RAG

Portfolio project
Liu Chang
Scope & Challenge: Tasked with improving mathematical reasoning in an instruction-tuned LLM. The core challenge was overcoming a low baseline accuracy and frequent reasoning errors caused by missing contextual knowledge. Deliverables & Feedback: Engineered a two-stage pipeline using structured Chain-of-Thought (CoT) prompting and RAG to dynamically inject theorems. This reduced errors and boosted accuracy from 60% to 85%. The workflow now powers the client's B2B projects, securing an ongoing long-term technical partnership.

1 like · 1 view · Sep 15, 2026

Scope & Challenge: Tasked with improving mathematical reasoning in an instruction-tuned LLM.

Tags