Loquacity and Visible Emotion: ChatGPT as a Policy Advisor

TL;DR

This paper evaluates ChatGPT's effectiveness as a policy advisor by testing its ability to produce policy briefs, highlighting its speed and structure but also its need for expert supervision and potential superficiality.

Contribution

It provides an empirical assessment of ChatGPT's capabilities and limitations in complex policy writing tasks, emphasizing the importance of supervision.

Findings

ChatGPT accelerates policy writing with well-structured suggestions.

It produces linguistically correct text quickly but needs expert oversight.

Naive use can lead to incorrect or superficial outputs.

Abstract

ChatGPT, a software seeking to simulate human conversational abilities, is attracting increasing attention. It is sometimes portrayed as a groundbreaking productivity aid, including for creative work. In this paper, we run an experiment to assess its potential in complex writing tasks. We ask the software to compose a policy brief for the Board of the Bank of Italy. We find that ChatGPT can accelerate workflows by providing well-structured content suggestions, and by producing extensive, linguistically correct text in a matter of seconds. It does, however, require a significant amount of expert supervision, which partially offsets productivity gains. If the app is used naively, output can be incorrect, superficial, or irrelevant. Superficiality is an especially problematic limitation in the context of policy advice intended for high-level audiences.