用梯度注入提升多模态模型推理能力，省数据少算力
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
- 从纯文本推理模型提取知识，通过梯度偏置注入多模态模型
- 在MathVista和MathVerse上超越基线方法，性能接近训练密集型方案
- 无需复杂训练，适合资源有限时快速增强模型推理能力
多模态大语言模型（MLLM）发展迅速，但其推理能力常落后于纯文本大模型。传统补救方法需大量多模态推理数据或强化学习，成本高昂。现有参数融合方法虽轻量，但效果不稳定，尤其对Qwen系列模型易导致性能下降。本文提出方向性推理注入微调（DRIFT），通过预计算文本推理专家与多模态模型的参数差异，生成推理先验，并在监督微调中以梯度偏置方式注入该先验，保持多模态对齐的同时高效传递推理能力。该方法兼容标准SFT流程，在MathVista和MathVerse等多模态推理基准上显著优于直接合并与标准SFT，且达到甚至超过高成本训练方法的效果，同时大幅降低数据与计算开销。
原文摘要 · Abstract (English)
Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-scale multimodal reasoning data or reinforcement learning, incurring substantial cost. An appealing alternative is parameter-space model merging between reasoning-enhanced LLMs and MLLMs, but we show that naive merging is fragile: its effectiveness varies widely across model families and can significantly degrade performance (e.g., for Qwen-based MLLMs). We propose Directional Reasoning Injection for Fine-Tuning (DRIFT), a lightweight method that transfers reasoning knowledge in the gradient space while preserving multimodal alignment. DRIFT precomputes a reasoning prior from the parameter differences between text-only reasoning experts and multimodal models, and uses it to bias gradients during supervised fine-tuning. This design retains the simplicity of standard SFT pipelines while enabling efficient and stable reasoning transfer. Experiments on multimodal reasoning benchmarks, including MathVista and MathVerse, show that DRIFT consistently outperforms naive merging and standard SFT, and matches or surpasses training-intensive methods with substantially lower data and compute.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。