Ornithologist: Towards Trustworthy "Reasoning" about Central Bank Communications

TL;DR

Ornithologist is a weakly-supervised, transparent textual classification system that assesses central bank communication tone, improving explainability and applicability while predicting future monetary policy movements.

Contribution

It introduces taxonomy-guided reasoning with large language models for trustworthy, low-supervision classification of central bank text, enhancing transparency and reducing hallucination risk.

Findings

Measurements predict future cash rate movements.

System is accessible to non-experts.

Reduces supervision compared to traditional methods.

Abstract

I develop Ornithologist, a weakly-supervised textual classification system and measure the hawkishness and dovishness of central bank text. Ornithologist uses ``taxonomy-guided reasoning'', guiding a large language model with human-authored decision trees. This increases the transparency and explainability of the system and makes it accessible to non-experts. It also reduces hallucination risk. Since it requires less supervision than traditional classification systems, it can more easily be applied to other problems or sources of text (e.g. news) without much modification. Ornithologist measurements of hawkishness and dovishness of RBA communication carry information about the future of the cash rate path and of market expectations.