每日文献雷达

2026-07-15

今日入选

• LLM-Enhanced Data Management（topic keywords matched; 19 citations; appeared 5x before）
• Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction（code signal; 16 citations; appeared 3x before）
• Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers（topic keywords matched; 1 citations; appeared 5x before）
• Rethinking Tabular Data Understanding with Large Language Models（54 citations; appeared 5x before）
• Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks（214 citations; appeared 3x before）

1. LLM-Enhanced Data Management

        - **来源**：deepxiv
        - **分数**：0.19
        - **入选原因**：topic keywords matched; 19 citations; appeared 5x before
        - **摘要**：Machine learning (ML) techniques for optimizing data management problems have been extensively studied and widely deployed in recent five years. However traditional ML methods have limitations on generalizability (adapting to different scenarios) and inference ability (understand...

• 链接：https://arxiv.org/abs/2402.02643

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

2. Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction

        - **来源**：deepxiv
        - **分数**：0.1827
        - **入选原因**：code signal; 16 citations; appeared 3x before
        - **摘要**：With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance. However, existing prompt-based learning methods for knowledge graph construction are still susc...

• 链接：https://arxiv.org/abs/2210.10709

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

3. Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers

        - **来源**：deepxiv
        - **分数**：0.18
        - **入选原因**：topic keywords matched; 1 citations; appeared 5x before
        - **摘要**：Tracking how data is mentioned and used in research papers provides critical insights for improving data discoverability, quality, and production. However, manually identifying and classifying dataset mentions across vast academic literature is resource-intensive and not scalable...

• 链接：https://arxiv.org/abs/2502.10263

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

4. Rethinking Tabular Data Understanding with Large Language Models

        - **来源**：deepxiv
        - **分数**：0.1574
        - **入选原因**：54 citations; appeared 5x before
        - **摘要**：Large Language Models (LLMs) have shown to be capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area. In this context, this study investigates from three core perspectives: the robustness of LLMs to structural ...

• 链接：https://arxiv.org/abs/2312.16702

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

5. Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

        - **来源**：deepxiv
        - **分数**：0.11
        - **入选原因**：214 citations; appeared 3x before
        - **摘要**：We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate "few-shot" models for classes existing at the tail of the class distribution, for which little data i...

• 链接：https://arxiv.org/abs/1903.01306

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>