Testing prompt engineering methods for knowledge extraction from text

Abstract

The capabilities of Large Language Models (LLMs,) such as Mistral 7B, Llama 3, GPT-4, present a significant opportunity for knowledge extraction (KE) from text. However, LLMs’ context-sensitivity can hinder obtaining precise and task-aligned outcomes, thereby requiring prompt engineering. This study explores the efficacy of five prompt methods with different task demonstration strategies across 17 different prompt templates, utilizing a relation extraction dataset (RED-FM) with the aforementioned LLMs. To facilitate evaluation, we introduce a novel framework grounded in Wikidata’s ontology. The findings demonstrate that LLMs are capable of extracting a diverse array of facts from text. Notably, incorporating a simple instruction accompanied by a task demonstration – comprising three examples selected via a retrieval mechanism – significantly enhances performance across Mistral 7B, Llama 3, and GPT-4. The effectiveness of reasoning-oriented prompting methods such as Chain-of-Thought, Reasoning and Acting, while improved with task demonstrations, does not surpass alternative methods. This suggests that framing extraction as a reasoning task may not be necessary for KE. Notably, task demonstrations leveraging examples selected via retrieval mechanisms facilitate effective knowledge extraction across all tested prompting strategies and LLMs.

Abstract of "Testing prompt engineering methods for knowledge extraction from text" by Fina Polat, Ilaria Tiddi, Paul Groth, https://doi.org/10.3233/sw-243719, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.