DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations
This addresses the problem of limited annotated data for researchers and practitioners in document-level information extraction, but it is incremental as it builds on existing in-context learning methods.
The paper tackled the scarcity of annotated corpora for document-level entity and relation extraction by developing a fully automatic, LLM-based pipeline for synthetic data generation and in-context learning, producing a dataset of over 5k Wikipedia abstracts with approximately 59k entities and 30k relation triples, and found that in-context joint extraction remains challenging for state-of-the-art models.
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.