Year: 2025
Type: preprint
Abstract: While Reinforcement Learning with Verifiable Rewards has enhanced the reasoning of large-scale language models (LLMs), its efficacy for lightweight multimodal language models (MLLMs) with fewer than seven billion parameters remains underexplored. This paper investigates the role of long Chain-of-Thought (long CoT) data in enhancing the reasoning abilities of such MLLMs. Our findings demonstrate that Supervised Fine-Tuning (SFT) with long CoT data significantly improves MLLM reasoning. Furthermore, we observe that after this initial SFT phase, MLLMs can achieve additional performance gains through a subsequent RL stage. We conclude that a SFT stage with long CoT data is a critical prerequisite for developing the reasoning capabilities of lightweight MLLMs.
Source: arXiv (Cornell University)
Authors: Ou, Linyu, Yin, YuYang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417413600
Cites:
Cited by:
Related to: