通过知识协同蒸馏解析文本与图结构在关系推理中的互补机制
$R^2$-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation
- 构建统一框架实现文本与图表示的协同蒸馏
- 在5个关系推理任务中发现双模态表征的对齐与分化模式
- 揭示融合时机与效果，适合研究多模态模型可解释性者
关系推理是许多自然语言处理任务的核心，依赖于文本和图结构提供的互补信息。尽管已有研究探索如何利用这种双重互补性，但对文本-图交互机制及其对混合模型影响的系统性理解仍不充分。本文采用分析驱动的方法，通过支持知识协同蒸馏（CoD）的统一架构，探究文本与图表示的互补性。我们考察了五个在信息编码方式上不同的关系推理任务，通过追踪训练过程中双模态表征的演化过程，发现了可解释的对齐与分化模式，并揭示了其融合的适用条件与优势。
原文摘要 · Abstract (English)
Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual complementarity, a detailed and systematic understanding of text-graph interplay and its effect on hybrid models remains underexplored. We take an analysis-driven approach to investigate text-graph representation complementarity via a unified architecture that supports knowledge co-distillation (CoD). We explore five tasks involving relational reasoning that differ in how text and graph structures encode the information needed to solve that task. By tracking how these dual representations evolve during training, we uncover interpretable patterns of alignment and divergence, and provide insights into when and why their integration is beneficial.
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。