CM1 - A Dataset for Evaluating Few-Shot Information Extraction with Large Vision Language Models

• URL: http://arxiv.org/abs/2505.04214v1
• Date: Wed, 07 May 2025 08:08:58 GMT
• Title: CM1 - A Dataset for Evaluating Few-Shot Information Extraction with Large Vision Language Models
• Authors: Fabian Wolf, Oliver Tüselmann, Arthur Matei, Lukas Hennies, Christoph Rass, Gernot A. Fink,
• Abstract summary: Large Vision Language Models (LVLM) are a promising technology to tackle this problem.<n>We present a novel dataset specifically designed to evaluate the few-shot capabilities of LVLMs.
• Score: 2.3749905164931207
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The automatic extraction of key-value information from handwritten documents is a key challenge in document analysis. A reliable extraction is a prerequisite for the mass digitization efforts of many archives. Large Vision Language Models (LVLM) are a promising technology to tackle this problem especially in scenarios where little annotated training data is available. In this work, we present a novel dataset specifically designed to evaluate the few-shot capabilities of LVLMs. The CM1 documents are a historic collection of forms with handwritten entries created in Europe to administer the Care and Maintenance program after World War Two. The dataset establishes three benchmarks on extracting name and birthdate information and, furthermore, considers different training set sizes. We provide baseline results for two different LVLMs and compare performances to an established full-page extraction model. While the traditional full-page model achieves highly competitive performances, our experiments show that when only a few training samples are available the considered LVLMs benefit from their size and heavy pretraining and outperform the classical approach.

Related papers

• Generative Compositor for Few-Shot Visual Information Extraction [60.663887314625164]
  We propose a novel generative model, named Generative generative spatialtor, to address the challenge of few-shot VIE.<n>Generative generative spatialtor is a hybrid pointer-generator network that emulates the operations of a compositor by retrieving words from the source text.<n>The proposed method achieves highly competitive results in the full-sample training, while notably outperforms the baseline in the 1-shot, 5-shot, and 10-shot settings.
  arXiv  Detail & Related papers  (2025-03-21T04:56:24Z)
• Is This Collection Worth My LLM's Time? Automatically Measuring Information Potential in Text Corpora [2.3251886193174114]
  We present an automated pipeline that evaluates the potential information gain from text collections without requiring model training or fine-tuning.<n>Our method generates multiple choice questions (MCQs) from texts and measures an LLM's performance both with and without access to the source material.<n>Our results demonstrate that this method effectively identifies collections containing valuable novel information, providing a practical tool for prioritizing data acquisition and integration efforts.
  arXiv  Detail & Related papers  (2025-02-19T13:03:06Z)
• SAIL: Sample-Centric In-Context Learning for Document Information Extraction [4.262937373782431]
  Document Information Extraction (DIE) aims to extract structured information from Visually Rich Documents (VRDs)<n>Previous full-training approaches have demonstrated strong performance but may struggle with generalization to unseen data.<n>We propose Sample-centric In-context Learning (SAIL) for DIE to provide accurate guidance to pre-trained models.
  arXiv  Detail & Related papers  (2024-12-22T16:58:59Z)
• Using Large Language Models to Enrich the Documentation of Datasets for Machine Learning [1.8270184406083445]
  We explore using large language models (LLM) and prompting strategies to automatically extract dimensions from documents. Our approach could aid data publishers and practitioners in creating machine-readable documentation. We have released an open-source tool implementing our approach and a replication package, including the experiments' code and results.
  arXiv  Detail & Related papers  (2024-04-04T10:09:28Z)
• Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models [29.94694305204144]
  We present a novel framework for document-level in-context few-shot relation extraction. We evaluate our framework using DocRED, the largest publicly available dataset for document-level relation extraction.
  arXiv  Detail & Related papers  (2023-10-17T09:10:27Z)
• Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes [54.13559879916708]
  EVAPORATE is a prototype system powered by large language models (LLMs)<n>Code synthesis is cheap, but far less accurate than directly processing each document with the LLM.<n>We propose an extended code implementation, EVAPORATE-CODE+, which achieves better quality than direct extraction.
  arXiv  Detail & Related papers  (2023-04-19T06:00:26Z)
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
  GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks. We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate. We build the first conversation-based information retrieval dataset employing AnnoLLM.
  arXiv  Detail & Related papers  (2023-03-29T17:03:21Z)
• ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction [56.790794611002106]
  Large language models (LLMs) have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning. We propose a simple but effective in-context learning framework called ICL-D3IE. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations.
  arXiv  Detail & Related papers  (2023-03-09T06:24:50Z)
• Recitation-Augmented Language Models [85.30591349383849]
  We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks. Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-10-04T00:49:20Z)
• Multi-Document Summarization with Centroid-Based Pretraining [35.8335939654861]
  In Multi-Document Summarization (MDS), the input can be modeled as a set of documents, and the output is its summary. We introduce a novel pretraining objective, which involves selecting the ROUGE-based centroid of each document cluster as a proxy for its summary. Our objective thus does not require human written summaries and can be utilized for pretraining on a dataset consisting solely of document sets.
  arXiv  Detail & Related papers  (2022-08-01T17:28:02Z)
• PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization [16.830963601598242]
  We propose PRIMER, a pre-trained model for multi-document representation with focus on summarization. Specifically, we adopt the Longformer architecture with proper input transformation and global attention to fit for multi-document inputs. Our model, PRIMER, outperforms current state-of-the-art models on most of these settings with large margins.
  arXiv  Detail & Related papers  (2021-10-16T07:22:24Z)
• One-shot Key Information Extraction from Document with Deep Partial Graph Matching [60.48651298832829]
  Key Information Extraction (KIE) from documents improves efficiency, productivity, and security in many industrial scenarios. Existing supervised learning methods for the KIE task need to feed a large number of labeled samples and learn separate models for different types of documents. We propose a deep end-to-end trainable network for one-shot KIE using partial graph matching.
  arXiv  Detail & Related papers  (2021-09-26T07:45:53Z)

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.