让不同分词器的模型也能高效互学推理能力
CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers
- 用思维链增强+最优传输对齐，跨分词器知识迁移
- 在多领域任务中提升学生模型推理能力与鲁棒性
- 适合需部署小模型但保留大模型推理能力的场景
大语言模型在多项自然语言任务中表现卓越，但高昂的计算成本与内存限制制约其部署。知识蒸馏（KD）通过将大模型知识迁移到小模型来缓解该问题。然而，现有方法常假设共享词表和分词器，灵活性受限。尽管通用逻辑蒸馏（ULD）和双空间知识蒸馏（DSKD）处理了词汇不匹配问题，却忽视了关键的‘推理感知蒸馏’。为此，我们提出CoT2Align，一种融合思维链增强与跨思维链对齐的通用蒸馏框架。进一步将最优传输扩展至序列级与层级对齐，适应不同序列长度并保持上下文完整性。大量实验表明，CoT2Align在多种词表设置下均优于现有方法，显著提升学生模型的推理能力与领域任务鲁棒性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) achieve state-of-the-art performance across various NLP tasks but face deployment challenges due to high computational costs and memory constraints. Knowledge distillation (KD) is a promising solution, transferring knowledge from large teacher models to smaller student models. However, existing KD methods often assume shared vocabularies and tokenizers, limiting their flexibility. While approaches like Universal Logit Distillation (ULD) and Dual-Space Knowledge Distillation (DSKD) address vocabulary mismatches, they overlook the critical \textbf{reasoning-aware distillation} aspect. To bridge this gap, we propose CoT2Align a universal KD framework that integrates Chain-of-Thought (CoT) augmentation and introduces Cross-CoT Alignment to enhance reasoning transfer. Additionally, we extend Optimal Transport beyond token-wise alignment to a sequence-level and layer-wise alignment approach that adapts to varying sequence lengths while preserving contextual integrity. Comprehensive experiments demonstrate that CoT2Align outperforms existing KD methods across different vocabulary settings, improving reasoning capabilities and robustness in domain-specific tasks.
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。