JRE-L:面向普通受众的科学新闻学中 Journalist、Reader 和 Editor LLMs 在环交互
JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience
AI总结:
提出 JRE-L 框架,通过集成三个 LLM 模拟记者、读者和编辑的写作-阅读-反馈-修订循环,利用开源小模型协作生成比 GPT-4 等现有方法更易懂的科学新闻文章。
摘要:
科学新闻学向非专业人士报道当前的科学发现,旨在使公众能够理解最新进展。由于受众通常缺乏关于所展示研究的具体知识,这项任务极具挑战性。我们提出了一个 JRE-L 框架,该框架集成了三个 LLM,模拟写作-阅读-反馈-修订的循环。在 JRE-L 中,一个 LLM 充当记者,另一个 LLM 充当普通公众读者,第三个 LLM 充当编辑。记者的写作通过读者的反馈和编辑的建议进行迭代优化。我们的实验表明,通过利用两个 7B 和一个 1.8B 开源 LLM 的协作,我们能够生成比现有方法(包括提示单个高级模型如 GPT-4 以及其他 LLM 协作策略)更具可读性的文章。我们的代码已在 github.com/Zzoay/JRE-L 公开。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。