每日文献雷达：2026-07-15

今日 slides：research-radar-2026-07-15

每日文献雷达：2026-07-15

今日自动检索并筛选出 5 篇候选论文，通过结构化深度阅读生成以下分析。


flowchart TB
    subgraph TODAY["今日入选 2026-07-15"]
    P1["LLM-Enhanced Data Management..."]
    P2["Schema-aware Reference as Prompt Improves Data-Eff..."]
    P3["Large Language Models and Synthetic Data for Monit..."]
    P4["Rethinking Tabular Data Understanding with Large L..."]
    P5["Long-tail Relation Extraction via Knowledge Graph ..."]
    end
    TODAY --> BLOG["博客深度阅读"]
    BLOG --> SLIDES["Marp 幻灯片"]
    style TODAY fill:#f0f4ff,stroke:#4a90d9
    style BLOG fill:#d4edda,stroke:#155724
    style SLIDES fill:#e2d9f3,stroke:#6f42c1

今日入选

  • LLM-Enhanced Data Management（score: 0.19）
  • Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction（score: 0.1827）
  • Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers（score: 0.18）
  • Rethinking Tabular Data Understanding with Large Language Models（score: 0.1574）
  • Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks（score: 0.11）

LLM-Enhanced Data Management

  • 作者：Xuanhe Zhou, Xinyang Zhao, Guoliang Li
  • 入选原因：topic keywords matched; 19 citations; appeared 5x before
  • 来源信息：发表：arXiv.org | 引用：19 | 链接：https://arxiv.org/abs/2402.02643

Machine learning (ML) techniques for optimizing data management problems have been extensively studied and widely deployed in recent five years.

  • 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 (understanding the context). Fortunately, large language models (LLMs) have shown high generalizability and human-competitive abilities in understanding context, which are promising for data management tasks (e.g., database diagnosis, database tuning). However, existing LLMs have several limitations: hallucination, high cost, and low accuracy for complicated tasks. To address these challenges, we design LLMDB, an LLM-enhanced data management paradigm which has generalizability and high inference ability while avoiding halluci…

  • 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

  • 实验：需确认数据集、指标和 baseline。

  • 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

  • 后续动作：深读方法和实验设计，建议人工使用 /readpaper 精读

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

  • 作者：Yunzhi Yao, Shengyu Mao, Ningyu Zhang, Xiang Chen, Shumin Deng et al.
  • 入选原因：code signal; 16 citations; appeared 3x before
  • 来源信息：发表：Annual International ACM SIGIR Conference on Research and Development in Information Retrieval | 引用：16 | 代码：https://github.com/zjunlp/RAP | 链接：https://arxiv.org/abs/2210.10709

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.

  • 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 susceptible to several potential limitations: (i) semantic gap between natural language and output structured knowledge with pre-defined schema, which means model cannot fully exploit semantic knowledge with the constrained templates; (ii) representation learning with locally individual instances limits the performance given the insufficient features, which are unable to unleash the potential analogical capability of pre-trained language models. Motivated by these observations, we propose a retrieval-augmented approach…

  • 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

  • 实验：需确认数据集、指标和 baseline。

  • 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

  • 后续动作：保留为快读候选，后续按主题相关性跟进

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

  • 作者：Aivin V. Solatorio, Rafael Macalaba, James Liounis
  • 入选原因：topic keywords matched; 1 citations; appeared 5x before
  • 来源信息：发表：arXiv.org | 引用：1 | 链接：https://arxiv.org/abs/2502.10263

Tracking how data is mentioned and used in research papers provides critical insights for improving data discoverability, quality, and production.

  • 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. This paper presents a machine learning framework that automates dataset mention detection across research domains by leveraging large language models (LLMs), synthetic data, and a two-stage fine-tuning process. We employ zero-shot extraction from research papers, an LLM-as-a-Judge for quality assessment, and a reasoning agent for refinement to generate a weakly supervised synthetic dataset. The Phi-3.5-mini instruct model is pre-fine-tuned on this dataset, followed by fine-tuning on a manually annotated subset. A…

  • 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

  • 实验：需确认数据集、指标和 baseline。

  • 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

  • 后续动作：保留为快读候选，后续按主题相关性跟进

Rethinking Tabular Data Understanding with Large Language Models

  • 作者：Tianyang Liu, Fei Wang, Muhao Chen
  • 入选原因：54 citations; appeared 5x before
  • 来源信息：发表：North American Chapter of the Association for Computational Linguistics | 引用：54 | 链接：https://arxiv.org/abs/2312.16702

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.

  • 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 perturbations in tables, the comparative analysis of textual and symbolic reasoning on tables, and the potential of boosting model performance through the aggregation of multiple reasoning pathways. We discover that structural variance of tables presenting the same content reveals a notable performance decline, particularly in symbolic reasoning tasks. This prompts the proposal of a method for table structure normalization. Moreover, textual reasoning slightly edges out symbolic reasoning, and a detailed error anal…

  • 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

  • 实验：需确认数据集、指标和 baseline。

  • 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

  • 后续动作：保留为快读候选，后续按主题相关性跟进

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

  • 作者：Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen et al.
  • 入选原因：214 citations; appeared 3x before
  • 来源信息：发表：North American Chapter of the Association for Computational Linguistics | 引用：214 | 链接：https://arxiv.org/abs/1903.01306

We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings.

  • 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 is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extractio…

  • 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

  • 实验：需确认数据集、指标和 baseline。

  • 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

  • 后续动作：保留为快读候选，后续按主题相关性跟进

检索说明

  • 检索层：arXiv（deepxiv）+ Semantic Scholar + Google Scholar，每日查询轮换，保证论文多样性。
  • 阅读层：优先获取 arXiv HTML 全文，使用结构化三元组 + 公众号 storytelling 风格拆解论文逻辑。
  • 深度阅读方法论参考 /readpaper 技能。
  • 自动分析用于雷达筛选，重要论文仍需人工复核。
Research Radar
#literature #research-agent #data-analysis-agent
每日文献雷达：2026-07-15
http://zkkk123.cn/2026/07/15/research-radar/2026-07-15-daily-research-radar/
Author
Ke Zhang
Posted on
July 15, 2026
Licensed under