Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.