Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.09756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910526658838528 |
|---|---|
| author | Jiang, Gongyao Shi, Xinran Luo, Qiong |
| author_facet | Jiang, Gongyao Shi, Xinran Luo, Qiong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09756 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM-Collaboration on Automatic Science Journalism for the General Audience Jiang, Gongyao Shi, Xinran Luo, Qiong Computation and Language 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. |
| title | LLM-Collaboration on Automatic Science Journalism for the General Audience |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.09756 |