今日 slides：research-radar-2026-07-13

每日文献雷达：2026-07-13

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 2026-07-13"]
    P1["LLM As DBA..."]
    P2["MoMQ: Mixture-of-Experts Enhances Multi-Dialect Qu..."]
    P3["Schema-adaptable Knowledge Graph Construction..."]
    P4["MMTU: A Massive Multi-Task Table Understanding and..."]
    P5["Fine-Tuning Language Models for Context-Specific S..."]
    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 As DBA（score: 0.2655）
• MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases（score: 0.2561）
• Schema-adaptable Knowledge Graph Construction（score: 0.2441）
• MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark（score: 0.2436）
• Fine-Tuning Language Models for Context-Specific SQL Query Generation（score: 0.2378）

---

LLM As DBA

• 作者：Xuanhe Zhou, Guoliang Li, Zhiyuan Liu
• 入选原因：code signal; 21 citations; appeared 2x before
• 来源信息：引用：21 | 链接：https://arxiv.org/abs/2308.05481

Database administrators (DBAs) play a crucial role in managing, maintaining and optimizing a database system to ensure data availability, performance, and reliability.

• 摘要：Database administrators (DBAs) play a crucial role in managing, maintaining and optimizing a database system to ensure data availability, performance, and reliability. However, it is hard and tedious for DBAs to manage a large number of database instances (e.g., millions of instances on the cloud databases). Recently large language models (LLMs) have shown great potential to understand valuable documents and accordingly generate reasonable answers. Thus, we propose D-Bot, a LLM-based database administrator that can continuously acquire database maintenance experience from textual sources, and provide reasonable, well-founded, in-time diagnosis and optimization advice for target databases. This paper presents a revolutionary LLM-centric framework for database maintenance, including (i) data…

• 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

---

MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases

• 作者：Zhisheng Lin, Yifu Liu, Zhiling Luo, Jinyang Gao, Yu Li
• 入选原因：6 citations; appeared 1x before
• 来源信息：发表：arXiv.org | 引用：6 | 链接：https://arxiv.org/abs/2410.18406

The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs).

• 摘要：The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntactic differences among dialects and imbalanced data distribution across multiple dialects. To tackle these challenges, we propose MoMQ, a novel Mixture-of-Experts-based multi-dialect query generation fra…

• 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

---

Schema-adaptable Knowledge Graph Construction

• 作者：Hongbin Ye, Honghao Gui, Xin Xu, Xi Chen, Huajun Chen et al.
• 入选原因：code signal; 6 citations; appeared 2x before
• 来源信息：发表：Conference on Empirical Methods in Natural Language Processing | 引用：6 | 代码：https://github.com/zjunlp/AdaKGC | 链接：https://arxiv.org/abs/2305.08703

Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema.

• 摘要：Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a system that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion; then investigate the sc…

• 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

---

MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark

• 作者：Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han et al.
• 入选原因：code signal; 13 citations; appeared 3x before
• 来源信息：发表：arXiv.org | 引用：13 | 代码：https://github.com/MMTU-Benchmark/MMTU | 链接：https://arxiv.org/abs/2506.05587

Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engineers, data analysts, and database administrators to operate.

• 摘要：Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engineers, data analysts, and database administrators to operate. Although LLMs have shown remarkable progress in working with tables (e.g., in spreadsheet and database copilot scenarios), comprehensive benchmarking of such capabilities remains limited. In contrast to an extensive and growing list of NLP benchmarks, evaluations of table-related tasks are scarce, and narrowly focus on tasks like NL-to-SQL and Table-QA, overlooking the broader spectrum of real-world tasks that professional users face. This gap limits our understanding and model progress in this important area.\ In…

• 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

---

Fine-Tuning Language Models for Context-Specific SQL Query Generation

• 作者：Amine Rebei
• 入选原因：8 citations; appeared 1x before
• 来源信息：发表：arXiv.org | 引用：8 | 链接：https://arxiv.org/abs/2312.02251

The ability to generate SQL queries from natural language has significant implications for making data accessible to non-specialists.

• 摘要：The ability to generate SQL queries from natural language has significant implications for making data accessible to non-specialists. This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task of transforming natural language into SQL queries within the retail domain. We introduce models specialized in generating SQL queries, trained on synthetic datasets tailored to the Snowflake SQL and GoogleSQL dialects. Our methodology involves generating a context-specific dataset using GPT-4, then fine-tuning three open-source LLMs(Starcoder Plus, Code-Llama, and Mistral) employing the LoRa technique to optimize for resource constraints. The fine-tuned models demonstrate superior performance in zero-shot settings compared to the baseline GPT-4, with Cod…

• 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。