Saved in:
Bibliographic Details
Main Authors: Popovič, Nicholas, Kangen, Ashish, Schopf, Tim, Färber, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05997
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913932319391744
author Popovič, Nicholas
Kangen, Ashish
Schopf, Tim
Färber, Michael
author_facet Popovič, Nicholas
Kangen, Ashish
Schopf, Tim
Färber, Michael
contents Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning for document-level entity and relation extraction. In contrast to existing approaches that rely on manually annotated demonstrations or direct zero-shot inference, our method combines synthetic data generation with retrieval-based in-context learning, using a reasoning-optimized language model. This allows us to build a high-quality demonstration database without manual annotation and to dynamically retrieve relevant examples at inference time. Based on our approach we produce a synthetic dataset of over $5k$ Wikipedia abstracts with approximately $59k$ entities and $30k$ relation triples. Finally, we evaluate in-context learning performance on the DocIE shared task, extracting entities and relations from long documents in a zero-shot setting. We find that in-context joint entity and relation extraction at document-level remains a challenging task, even for state-of-the-art large language models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05997
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations
Popovič, Nicholas
Kangen, Ashish
Schopf, Tim
Färber, Michael
Computation and Language
Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning for document-level entity and relation extraction. In contrast to existing approaches that rely on manually annotated demonstrations or direct zero-shot inference, our method combines synthetic data generation with retrieval-based in-context learning, using a reasoning-optimized language model. This allows us to build a high-quality demonstration database without manual annotation and to dynamically retrieve relevant examples at inference time. Based on our approach we produce a synthetic dataset of over $5k$ Wikipedia abstracts with approximately $59k$ entities and $30k$ relation triples. Finally, we evaluate in-context learning performance on the DocIE shared task, extracting entities and relations from long documents in a zero-shot setting. We find that in-context joint entity and relation extraction at document-level remains a challenging task, even for state-of-the-art large language models.
title DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations
topic Computation and Language
url https://arxiv.org/abs/2507.05997