Theorem-SFT improves model reasoning by teaching theorem application

Researchers have developed a new method called Theorem-SFT to improve the generalization capabilities of supervised fine-tuned models. This approach shifts the focus from memorizing specific problem-solution pairs to understanding and applying explicit theorems. Theorem-SFT has shown significant performance improvements on mathematical reasoning benchmarks, including notable gains on MATH and GeoQA datasets when applied to LLaMA3.2-3B-Instruct and Qwen2.5-VL-7B-Instruct models. AI

IMPACT Enhances model reasoning by focusing on theorem application, potentially improving performance on complex tasks.

RANK_REASON Academic paper detailing a new method for improving model generalization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• GeoQA
• LLaMA3.2-3B-Instruct
• Qwen2.5-VL-7B-Instruct
• Ruiying Peng
• Theorem-SFT

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →