LLM-Collaboration on Automatic Science Journalism for the General Audience
This addresses the problem of public comprehension of scientific discoveries for general audiences, representing an incremental improvement in automated content generation.
The paper tackles the challenge of making science journalism accessible to non-specialists by proposing a framework that integrates three LLMs to mimic a writing-reading-feedback-revision workflow, resulting in articles that are more accessible than those generated by existing methods, including GPT-4.
Science journalism reports current scientific discoveries to non-specialists, aiming to enable public comprehension of the state of the art. However, this task can be challenging as the audience often lacks specific knowledge about the presented research. To address this challenge, we propose a framework that integrates three LLMs mimicking the real-world writing-reading-feedback-revision workflow, with one LLM acting as the journalist, a smaller 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 advanced models such as GPT-4.