JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience

TL;DR

The paper introduces JRE-L, a collaborative framework of three LLMs simulating the science journalism process to produce more accessible articles for the general public, outperforming existing single-model and collaboration methods.

Contribution

It presents a novel multi-LLM loop framework for science journalism that enhances accessibility of generated articles, leveraging open-source models.

Findings

Generated articles are more accessible than existing methods.

Collaboration of multiple LLMs improves quality over single models.

Open-source LLMs can effectively simulate journalism processes.

Abstract

Science journalism reports current scientific discoveries to non-specialists, aiming to enable public comprehension of the state of the art. This task is challenging as the audience often lacks specific knowledge about the presented research. We propose a JRE-L framework that integrates three LLMs mimicking the writing-reading-feedback-revision loop. In JRE-L, one LLM acts as the journalist, another LLM as the general public reader, and the third LLM as an editor. The journalist's writing is iteratively refined by feedback from the reader and suggestions from the editor. Our experiments demonstrate that by leveraging the collaboration of two 7B and one 1.8B open-source LLMs, we can generate articles that are more accessible than those generated by existing methods, including prompting single advanced models such as GPT-4 and other LLM-collaboration strategies. Our code is publicly available at github.com/Zzoay/JRE-L.