paper-with-me

Papers

Semantic Refinement with LLMs for Graph Representations

2025-12-24 · Safal Thapaliya, Zehong Wang, Jiazheng Li, Ziming Li, Yanfang Ye, Chuxu Zhang arxiv

Graph-structured data exhibit substantial heterogeneity in where their predictive signals originate: in some domains, node-level semantics dominate, while in others, structural patterns play a central role. This structure-semantics heterogeneity implies that no graph learning model with a fixed inductive bias can generalize optimally across diverse graph domains. However, most existing methods address this challenge from the model side by incrementally injecting new inductive biases, which remains fundamentally limited given the open-ended diversity of real-world graphs. In this work, we take a data-centric perspective and treat node semantics as a task-adaptive variable. We propose a Graph-Exemplar-guided Semantic Refinement (GES) framework for graph representation learning which -- unlike existing LLM-enhanced methods that generate node descriptions without graph context -- leverages structurally and semantically similar nodes from the graph itself to guide semantic refinement. Specifically, a GNN is first trained to produce predictive states, which along with structural and semantic similarity are used to retrieve in-graph exemplars that inform an LLM in refining node descriptions. We evaluate our approach on both text-rich and text-free graphs. Results show consistent improvements on semantics-rich and structure-dominated graphs, demonstrating the effectiveness of data-centric semantic refinement under structure-semantics heterogeneity.

📄 PDF Abstract BibTeX arXiv:2512.21106

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation LearningSemantic SimilarityGraph Learning

Similar Papers 제목 키워드 기반

TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning

2026-06-10 · Ruxue Shi, Yili Wang, Mengnan Du, Hangting Ye 외 arxiv

Few-shot tabular learning provides a cost-effective approach for real-world applications where annotation is costly and collecting sufficient samples for new tasks is difficult. Existing Traditional and LLM-based methods…

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement

2025-09-29 · Yu-Che Tsai, Kuan-Yu Chen, Yuan-Chi Li, Yuan-Hao Chen 외 arxiv

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative I…

Representation Learning

Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation

2025-04-13 · Zhiqing Cui, Jiahao Yuan, Hanqing Wang, Yanshu Li 외

Scientific diagrams are vital tools for communicating structured knowledge across disciplines. However, they are often published as static raster images, losing symbolic semantics and limiting reuse. While Multimodal Lar…

Code GenerationMultimodal Reasoningvalid

Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs

2026-03-14 · Xiaofei Zhu, Jinfei Chen, Feiyang Yuan, Zhou Yang arxiv

Recommendation systems aim to learn user interests from historical behaviors and deliver relevant items. Recent methods leverage large language models (LLMs) to construct and integrate semantic representations of users a…

Recommendation Systems

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

2026-03-04 · Zijin Hong, Hao Chen, Zheng Yuan, Qinggang Zhang 외 arxiv

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement task is subsequently i…