# DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations

arXiv: https://arxiv.org/abs/2507.05997 · HTML: https://mlsanity.com/paper/2507.05997/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [Few-Shot Document-Level Relation Extraction](https://mlsanity.com/paper/2205.02048/) (2022)
- [The Effects of Hallucinations in Synthetic Training Data for Relation Extraction](https://mlsanity.com/paper/2410.08393/) (2024)

## Built on by (most cited first, 1 of 1)

- [CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs](https://mlsanity.com/paper/2512.19305/) (2025)

## Abstract (arXiv)

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.