StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation

• URL: http://arxiv.org/abs/2507.21340v1
• Date: Mon, 28 Jul 2025 21:20:44 GMT
• Title: StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation
• Authors: Satyananda Kashyap, Sola Shirai, Nandana Mihindukulasooriya, Horst Samulowitz,
• Abstract summary: StructText is an end-to-end framework for automatically generating high-fidelity benchmarks for key-value extraction from text.<n>We evaluate the proposed method on 71,539 examples across 49 documents.
• Score: 8.251302684712773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extracting structured information from text, such as key-value pairs that could augment tabular data, is quite useful in many enterprise use cases. Although large language models (LLMs) have enabled numerous automated pipelines for converting natural language into structured formats, there is still a lack of benchmarks for evaluating their extraction quality, especially in specific domains or focused documents specific to a given organization. Building such benchmarks by manual annotations is labour-intensive and limits the size and scalability of the benchmarks. In this work, we present StructText, an end-to-end framework for automatically generating high-fidelity benchmarks for key-value extraction from text using existing tabular data. It uses available tabular data as structured ground truth, and follows a two-stage ``plan-then-execute'' pipeline to synthetically generate corresponding natural-language text. To ensure alignment between text and structured source, we introduce a multi-dimensional evaluation strategy that combines (a) LLM-based judgments on factuality, hallucination, and coherence and (b) objective extraction metrics measuring numeric and temporal accuracy. We evaluated the proposed method on 71,539 examples across 49 datasets. Results reveal that while LLMs achieve strong factual accuracy and avoid hallucination, they struggle with narrative coherence in producing extractable text. Notably, models presume numerical and temporal information with high fidelity yet this information becomes embedded in narratives that resist automated extraction. We release a framework, including datasets, evaluation tools, and baseline extraction systems, to support continued research.

Related papers

• Analise Semantica Automatizada com LLM e RAG para Bulas Farmaceuticas [0.0]
  This work investigates the use of RAG (Retrieval-Augmented Generation) architectures combined with Large-Scale Language Models (LLMs) to automate the analysis of documents in PDF format.<n>The proposal integrates vector search techniques by embeddings, semantic data extraction and generation of contextualized natural language responses.
  arXiv  Detail & Related papers  (2025-07-07T17:48:15Z)
• Structuring the Unstructured: A Multi-Agent System for Extracting and Querying Financial KPIs and Guidance [54.25184684077833]
  We propose an efficient and scalable method for extracting quantitative insights from unstructured financial documents.<n>Our proposed system consists of two specialized agents: the emphExtraction Agent and the emphText-to-Agent
  arXiv  Detail & Related papers  (2025-05-25T15:45:46Z)
• Empirical Evaluation of Embedding Models in the Context of Text Classification in Document Review in Construction Delay Disputes [6.076874513889027]
  Text embeddings are numerical representations of text data, where words, phrases, or entire documents are converted into vectors of real numbers.<n>This paper presents our work in evaluating different embeddings through a comprehensive comparative analysis of four distinct models.<n>We employ both K-Nearest Neighbors (KNN) and Logistic Regression (LR) to perform binary classification tasks, specifically determining whether a text snippet is associated with 'delay' or 'not delay' within a labeled dataset.
  arXiv  Detail & Related papers  (2025-01-16T22:12:11Z)
• StrucText-Eval: Evaluating Large Language Model's Reasoning Ability in Structure-Rich Text [29.03935605732864]
  We introduce StrucText-Eval, a benchmark to evaluate how well large language models understand and reason through structured text. We show that while open-source LLMs achieve a maximum accuracy of 74.9% on the standard dataset, their performance drops significantly to 45.8% on the harder dataset. In contrast, human participants reach an accuracy of 92.6% on StrucText-Eval-Hard, highlighting LLMs' current limitations in handling intricate structural information.
  arXiv  Detail & Related papers  (2024-06-15T12:48:00Z)
• Learning to Extract Structured Entities Using Language Models [52.281701191329]
  Recent advances in machine learning have significantly impacted the field of information extraction. We reformulate the task to be entity-centric, enabling the use of diverse metrics. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP metric.
  arXiv  Detail & Related papers  (2024-02-06T22:15:09Z)
• Improving Text Embeddings with Large Language Models [59.930513259982725]
  We introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. We leverage proprietary LLMs to generate diverse synthetic data for hundreds of thousands of text embedding tasks across 93 languages. Experiments demonstrate that our method achieves strong performance on highly competitive text embedding benchmarks without using any labeled data.
  arXiv  Detail & Related papers  (2023-12-31T02:13:18Z)
• Instruct and Extract: Instruction Tuning for On-Demand Information Extraction [86.29491354355356]
  On-Demand Information Extraction aims to fulfill the personalized demands of real-world users. We present a benchmark named InstructIE, inclusive of both automatically generated training data, as well as the human-annotated test set. Building on InstructIE, we further develop an On-Demand Information Extractor, ODIE.
  arXiv  Detail & Related papers  (2023-10-24T17:54:25Z)
• ImPaKT: A Dataset for Open-Schema Knowledge Base Construction [10.073210304061966]
  ImPaKT is a dataset for open-schema information extraction consisting of around 2500 text snippets from the C4 corpus, in the shopping domain (product buying guides) We evaluate the power of this approach by fine-tuning the open source UL2 language model on a subset of the dataset, extracting a set of implication relations from a corpus of product buying guides, and conducting human evaluations of the resulting predictions.
  arXiv  Detail & Related papers  (2022-12-21T05:02:49Z)
• Text2Struct: A Machine Learning Pipeline for Mining Structured Data from Text [3.495405394644691]
  This paper presents an end-to-end machine learning pipeline, Text2Struct, including a text annotation scheme, training data processing, and machine learning implementation.<n>We formulated the mining problem as the extraction of metrics and units associated with numerals in the text.<n>Most predicted relations between numerals and entities were well matched to the ground-truth annotations.
  arXiv  Detail & Related papers  (2022-12-18T09:31:36Z)
• BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing [55.058258437125524]
  We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing. We benchmark eight language models, including two GPT-3 variants available only through an API. Our experiments show that encoder-decoder pretrained language models can achieve similar performance or surpass state-of-the-art methods for syntactic and semantic parsing when the model output is constrained to be valid.
  arXiv  Detail & Related papers  (2022-06-21T18:34:11Z)
• Benchmarking Multimodal AutoML for Tabular Data with Text Fields [83.43249184357053]
  We assemble 18 multimodal data tables that each contain some text fields. Our benchmark enables researchers to evaluate their own methods for supervised learning with numeric, categorical, and text features.
  arXiv  Detail & Related papers  (2021-11-04T09:29:16Z)
• Automatic Construction of Evaluation Suites for Natural Language Generation Datasets [17.13484629172643]
  We develop a framework to generate controlled perturbations and identify subsets in text-to-scalar, text-to-text, or data-to-text settings. We propose an evaluation suite made of 80 challenge sets, demonstrate the kinds of analyses that it enables and shed light onto the limits of current generation models.
  arXiv  Detail & Related papers  (2021-06-16T18:20:58Z)
• ToTTo: A Controlled Table-To-Text Generation Dataset [61.83159452483026]
  ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples. We introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. While usually fluent, existing methods often hallucinate phrases that are not supported by the table.
  arXiv  Detail & Related papers  (2020-04-29T17:53:45Z)
• Extractive Summarization as Text Matching [123.09816729675838]
  This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. We formulate the extractive summarization task as a semantic text matching problem. We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
  arXiv  Detail & Related papers  (2020-04-19T08:27:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.