paper-with-me

Papers

SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning

2025-10-02 · Shicheng Liu, Kai Sun, Lisheng Fu, Xilun Chen, Xinyuan Zhang, Zhaojiang Lin, Rulin Shao, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong arxiv

Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging. Existing methods either lack generalization or are resource-intensive due to per-page LLM inference. In this paper, we introduce SCRIBES (SCRIpt-Based Semi-Structured Content Extraction at Web-Scale), a novel reinforcement learning framework that leverages layout similarity across webpages within the same site as a reward signal. Instead of processing each page individually, SCRIBES generates reusable extraction scripts that can be applied to groups of structurally similar webpages. Our approach further improves by iteratively training on synthetic annotations from in-the-wild CommonCrawl data. Experiments show that our approach outperforms strong baselines by over 13% in script quality and boosts downstream question answering accuracy by more than 4% for GPT-4o, enabling scalable and resource-efficient web information extraction.

📄 PDF Abstract BibTeX arXiv:2510.01832

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningInformation ExtractionQuestion Answering

Similar Papers 제목 키워드 기반

semiPQA: A Study on Product Question Answering over Semi-structured Data

2022-05-01 · ECNLP (ACL) 2022 5 · Xiaoyu Shen, Gianni Barlacchi, Marco del Tredici, Weiwei Cheng 외

Product question answering (PQA) aims to automatically address customer questions to improve their online shopping experience. Current research mainly focuses on finding answers from either unstructured text, like produc…

AttributeQuestion AnsweringSentence

Label-Free Model Evaluation with Semi-Structured Dataset Representations

2021-12-01 · Xiaoxiao Sun, Yunzhong Hou, Hongdong Li, Liang Zheng

Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on datase…

regression

Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

2026-03-21 · Manie Tadayon, Mayank Gupta arxiv

Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet traditional RAG methods struggle when the search space is unknown or when documents are semi-structured or struct…

SKATE: A Natural Language Interface for Encoding Structured Knowledge

2020-10-20 · Clifton McFate, Aditya Kalyanpur, Dave Ferrucci, Andrea Bradshaw 외

In Natural Language (NL) applications, there is often a mismatch between what the NL interface is capable of interpreting and what a lay user knows how to express. This work describes a novel natural language interface t…

HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data

2025-08-25 · Jiyoon Myung, Jihyeon Park, Joohyung Han arxiv

User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retriev…

Recommendation Systems