Text-rich graphs, which integrate complex structural dependencies with abundant textual information, are ubiquitous yet remain challenging for existing learning paradigms. Conventional methods and even LLM-hybrids compress rich text into static embeddings or summaries before structural reasoning, creating an information bottleneck and detaching updates from the raw content. We argue that in text-rich graphs, the text is not merely a node attribute but the primary medium through which structural relationships are manifested. We introduce RAMP, a Raw-text Anchored Message Passing approach that moves beyond using LLMs as mere feature extractors and instead recasts the LLM itself as a graph-native aggregation operator. RAMP exploits the text-rich nature of the graph via a novel dual-representation scheme: it anchors inference on each node's raw text during each iteration while propagating dynamically optimized messages from neighbors. It further handles both discriminative and generative tasks under a single unified generative formulation. Extensive experiments show that RAMP effectively bridges the gap between graph propagation and deep text reasoning, achieving competitive performance and offering new insights into the role of LLMs as graph kernels for general-purpose graph learning.

翻译：文本丰富图融合了复杂的结构依赖性与丰富的文本信息，其应用广泛但现有学习范式仍面临挑战。传统方法甚至结合大语言模型（LLM）的混合方法通常在结构推理前将丰富文本压缩为静态嵌入或摘要，这会造成信息瓶颈并使更新过程与原始内容脱节。我们认为在文本丰富图中，文本不仅是节点属性，更是结构关系呈现的主要媒介。本文提出RAMP（Raw-text Anchored Message Passing）方法，该方法超越将LLM仅用作特征提取器的传统思路，将LLM本身重构为图原生的聚合算子。RAMP通过新颖的双重表示机制充分利用图的文本丰富特性：在每次迭代中基于各节点的原始文本进行推理，同时传播来自邻居的动态优化消息。该方法进一步在统一的生成式框架下处理判别式与生成式任务。大量实验表明，RAMP有效弥合了图传播与深度文本推理之间的鸿沟，在取得优异性能的同时，为LLM作为通用图学习中的图核函数角色提供了新的理论视角。