Improving citizen-government interactions with generative artificial intelligence: Novel human-computer interaction strategies for policy understanding through large language models
Lixin Yun, Sheng Yun, Haoran Xue, Fredrick Romanus Ishengoma, Jinran Wu, Jinran Wu · 2024
Read Improving citizen-government interactions with generative artificial intelligence: Novel human-computer interaction strategies for policy understanding through large language models by Lixin Yun, Sheng Yun, Haoran Xue, Fredrick Romanus Ishengoma, Jinran Wu, Jinran Wu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11651614.txt.
Description
Lixin Yun and co-authors present a 2024 paper on using generative AI to explain government policy to citizens. Policy texts are often complex and hard to reach, which weakens transparency and public engagement. The authors propose a chat system that answers citizen questions in plain, accurate language.
The system pairs a large language model with a retrieval step that fetches the right policy passages first. Tests used over two hundred policy documents from regional governments in China and the United States. Accuracy averaged 85.58 percent on the Chinese set and 90.67 percent on the American set. The authors present the design as a step past leaflets and static web pages, toward direct dialogue between citizens and the state.
Catalog record
| CREATOR | Lixin Yun, Sheng Yun, Haoran Xue, Fredrick Romanus Ishengoma, Jinran Wu, Jinran Wu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |