ChatGPT for Information Extraction

First page

Paper summary

A deeper assessment of ChatGPT on information extraction tasks.

Ask this paper

Key points

Extraction-task benchmark: Evaluates ChatGPT on named entity recognition, relation extraction, event extraction, and more.

Competitive but imperfect: Competitive with specialized IE models on many tasks but still falls short of fine-tuned SOTA on others.

Prompt sensitivity: Highlights significant prompt sensitivity in extraction outputs - practical challenges for deployment.

Practical assessment: A sober empirical reference informing whether to swap traditional IE pipelines for LLM-based alternatives.

Every Monday