Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths

TL;DR

This paper introduces an LLM-based framework that interprets Fedspeak by incorporating monetary policy context and uncertainty estimation, improving classification accuracy and reliability in understanding Federal Reserve communications.

Contribution

The paper presents a novel uncertainty-aware, domain-specific LLM framework for interpreting Fedspeak and classifying monetary policy stances, integrating policy transmission reasoning.

Findings

Achieves state-of-the-art accuracy in policy stance classification

Uncertainty correlates positively with model error rates

Enhances interpretability and confidence in Fedspeak analysis

Abstract

"Fedspeak", the stylized and often nuanced language used by the U.S. Federal Reserve, encodes implicit policy signals and strategic stances. The Federal Open Market Committee strategically employs Fedspeak as a communication tool to shape market expectations and influence both domestic and global economic conditions. As such, automatically parsing and interpreting Fedspeak presents a high-impact challenge, with significant implications for financial forecasting, algorithmic trading, and data-driven policy analysis. In this paper, we propose an LLM-based, uncertainty-aware framework for deciphering Fedspeak and classifying its underlying monetary policy stance. Technically, to enrich the semantic and contextual representation of Fedspeak texts, we incorporate domain-specific reasoning grounded in the monetary policy transmission mechanism. We further introduce a dynamic uncertainty decoding module to assess the confidence of model predictions, thereby enhancing both classification accuracy and model reliability. Experimental results demonstrate that our framework achieves state-of-the-art performance on the policy stance analysis task. Moreover, statistical analysis reveals a significant positive correlation between perceptual uncertainty and model error rates, validating the effectiveness of perceptual uncertainty as a diagnostic signal.