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

TL;DR

StructText is a framework that automatically generates high-quality benchmarks for key-value extraction from text, using existing tabular data and multi-dimensional evaluation to improve and assess LLM-based extraction methods.

Contribution

It introduces a novel synthetic data generation method and a multi-dimensional evaluation strategy for benchmarking key-value extraction from text.

Findings

LLMs show high factual accuracy and low hallucination in generated text.

Narrative coherence remains a challenge for extractability.

Numerical and temporal data are preserved with high fidelity in generated text.

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.