English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Open Information Extraction (OIE) task aims at extracting structured factsfrom unstructured text, typically in the form of (subject, relation, object)triples. Despite the potential of large language models (LLMs) like ChatGPT asa general task solver, they lag behind state-of-the-art (supervised) methods inOIE tasks due to two key issues. First, LLMs struggle to distinguish irrelevantcontext from relevant relations and generate structured output due to therestrictions on fine-tuning the model. Second, LLMs generates responsesautoregressively based on probability, which makes the predicted relations lackconfidence. In this paper, we assess the capabilities of LLMs in improving theOIE task. Particularly, we propose various in-context learning strategies toenhance LLM's instruction-following ability and a demonstration uncertaintyquantification module to enhance the confidence of the generated relations. Ourexperiments on three OIE benchmark datasets show that our approach holds itsown against established supervised methods, both quantitatively andqualitatively.

Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty