CLAIFeb 25, 2025

Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs

arXiv:2502.18179v35 citationsh-index: 18Has CodeEMNLP
Originality Incremental advance
AI Analysis

It addresses the challenge of efficiently extracting information from complex documents for users in fields like document processing, though it is incremental as it builds on existing LLM methods.

This paper tackles the problem of information extraction from layout-rich documents using large language models (LLMs) by defining a design space and optimizing configurations, resulting in an optimized LLM setup achieving 13.3–37.5 F1 points more than a baseline and matching specialized models with a cost-effective, finetuning-free approach.

This paper defines and explores the design space for information extraction (IE) from layout-rich documents using large language models (LLMs). The three core challenges of layout-aware IE with LLMs are 1) data structuring, 2) model engagement, and 3) output refinement. Our study investigates the sub-problems and methods within these core challenges, such as input representation, chunking, prompting, selection of LLMs, and multimodal models. It examines the effect of different design choices through LayIE-LLM, a new, open-source, layout-aware IE test suite, benchmarking against traditional, fine-tuned IE models. The results on two IE datasets show that LLMs require adjustment of the IE pipeline to achieve competitive performance: the optimized configuration found with LayIE-LLM achieves 13.3--37.5 F1 points more than a general-practice baseline configuration using the same LLM. To find a well-working configuration, we develop a one-factor-at-a-time (OFAT) method that achieves near-optimal results. Our method is only 0.8--1.8 points lower than the best full factorial exploration with a fraction (2.8%) of the required computation. Overall, we demonstrate that, if well-configured, general-purpose LLMs match the performance of specialized models, providing a cost-effective, finetuning-free alternative. Our test-suite is available at https://github.com/gayecolakoglu/LayIE-LLM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes