Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models

2026-03-15

AI Summary

This study addresses the challenge of accurately quantifying the implicit hawkish-dovish stance in Federal Reserve FOMC statements and its semantic evolution across meetings. To this end, the authors propose the Delta-Consistent Scoring (DCS) framework, which leverages frozen large language model (LLM) representations and employs self-supervised learning to jointly model both absolute policy stances and their relative shifts between consecutive meetings. A key innovation is the introduction of a delta consistency constraint that enables the construction of temporally coherent, unlabeled continuous stance trajectories without explicit annotations. Evaluated across four LLM backbones, DCS consistently outperforms supervised probing and LLM-as-judge baselines, achieving a sentence-level classification accuracy of 71.1%. The resulting meeting-level scores exhibit significant correlations with inflation indicators and Treasury yields, demonstrating the framework’s economic validity.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Federal Open Market Committee (FOMC) statements are a major source of monetary-policy information, and even subtle changes in their wording can move global financial markets. A central task is therefore to measure the hawkish--dovish stance conveyed in these texts. Existing approaches typically treat stance detection as a standard classification problem, labeling each statement in isolation. However, the interpretation of monetary-policy communication is inherently relative: market reactions depend not only on the tone of a statement, but also on how that tone shifts across meetings. We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large language model (LLM) representations to continuous stance scores by jointly modeling absolute stance and relative inter-meeting shifts. Rather than relying on manual hawkish--dovish labels, DCS uses consecutive meetings as a source of self-supervision. It learns an absolute stance score for each statement and a relative shift score between consecutive statements. A delta-consistency objective encourages changes in absolute scores to align with the relative shifts. This allows DCS to recover a temporally coherent stance trajectory without manual labels. Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification. The resulting meeting-level scores are also economically meaningful: they correlate strongly with inflation indicators and are significantly associated with Treasury yield movements. Overall, the results suggest that LLM representations encode monetary-policy signals that can be recovered through relative temporal structure.

Problem

• monetary policy stance
• FOMC statements
• hawkish-dovish classification
• temporal shifts
• natural language processing

Innovation

• Delta-Consistent Scoring
• monetary policy stance
• large language models
• self-supervision
• relative shift modeling