今日 slides：research-radar-2026-08-16

每日文献雷达：2026-08-16

今日自动检索并筛选出 1 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 2026-08-16"]
    P1["Auto-Fill: Learning to Predict Missing Values Accu..."]
    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

• Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models（score: 0.56）

---

Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models

• 作者：Yurong Liu, Yeye He, Haoyu Dong, Junjie Xing, Shi Han et al.
• 入选原因：published this month; code signal
• 来源信息：链接：https://arxiv.org/abs/2607.19847

Predicting missing cell values in tabular data is a fundamental problem in data cleaning.

• 摘要：Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically across rows and columns, they are costly to deploy at scale and tend to be overconfident, often generating hallucinated or false-positive predictions. In this paper, we observe that achieving high-precision missing-value prediction in tables requires a distinct combination of three capabilities: (1) world knowledge, (2) text-based reasoning, and (3) code-based reasoning. We systematically explore design choices for combining these capabilities, and propose an Auto-Fill approach that post-trains three specialist small language models (SLMs), each optimized for one capability. We …

• 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

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。