Ornithologist: Towards Trustworthy "Reasoning" about Central Bank Communications
This provides a more transparent and accessible tool for economists and policymakers to analyze central bank communications, though it is incremental in applying existing methods to a specific domain.
The paper tackles the problem of measuring hawkishness and dovishness in central bank communications by developing Ornithologist, a weakly-supervised textual classification system that uses taxonomy-guided reasoning with large language models, and finds that its measurements predict future cash rate paths and market expectations.
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.