Search Results
Working Paper
Artificial Intelligence and Inflation Forecasts
We explore the ability of Large Language Models (LLMs) to produce in-sample conditional inflation forecasts during the 2019-2023 period. We use a leading LLM (Google AI's PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years, and at almost all horizons. LLM forecasts exhibit slower reversion to the 2% inflation anchor.
Working Paper
What Do LLMs Want?
Large language models (LLMs) are now used for economic reasoning, but their implicit "preferences” are poorly understood. We study LLM preferences as revealed by their choices in simple allocation games and a job-search setting. Most models favor equal splits in dictator-style allocation games, consistent with inequality aversion. Structural estimates recover Fehr–Schmidt parameters that indicate inequality aversion is stronger than in similar experiments with human participants. However, we find these preferences are malleable: reframing (e.g., masking social context) and learned ...
Working Paper
Risk Management in Monetary Policy: A Review with Asset Pricing Implications
We review recent research on how the Fed's risk-management approach shapes the overall policy stance and how it affects financial market conditions. The evidence shows that the policy stance contains a forward-looking, conditional component that has long been an integral part of the Fed's policymaking toolkit. Asymmetric forward-looking policy tilts—motivated by risk-management considerations and revealed via the Fed’s communication—complement and extend beyond the effects of direct policy actions. Drawing on the transcripts of FOMC meetings between 1976 and 2019, we provide an ...
Working Paper
ChatMacro: Evaluating Inflation Forecasts of Generative AI
Recent research suggests that generic large language models (LLMs) can match the accuracy of traditional methods when forecasting macroeconomic variables in pseudo out-of-sample settings generated via prompts. This paper assesses the out-of-sample forecasting accuracy of LLMs by eliciting real-time forecasts of U.S. inflation from ChatGPT. We find that out-of-sample predictions are largely inaccurate and stale, even though forecasts generated in pseudo out-of-sample environments are comparable to existing benchmarks. Our results underscore the importance of out-of-sample benchmarking for LLM ...
Working Paper
Artificial Intelligence and Inflation Forecasts
We explore the ability of Large Language Models (LLMs) to produce conditional inflation forecasts during the 2019-2023 period. We use a leading LLM (Google AI's PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years, and at almost all horizons. LLM forecasts exhibit slower reversion to the 2% inflation anchor. We argue that this method of generating forecasts is inexpensive and can be ...
Working Paper
Evaluating Local Language Models: An Application to Bank Earnings Calls
This study evaluates the performance of local large language models (LLMs) in interpreting financial texts, compared with closed-source, cloud-based models. We first introduce new benchmarking tasks for assessing LLM performance in analyzing financial and economic texts and explore the refinements needed to improve its performance. Our benchmarking results suggest local LLMs are a viable tool for general natural language processing analysis of these texts. We then leverage local LLMs to analyze the tone and substance of bank earnings calls in the post-pandemic era, including calls conducted ...
Working Paper
Remote Work Across Jobs, Companies and Space
The pandemic catalyzed an enduring shift to remote work. To measure this shift, we develop a large language model (LLM), fine tune and assess it using 30,000 human classifications, and apply it to nearly 600 million job vacancy postings across five English-speaking countries. Our model achieves a 98% classification accuracy, greatly outperforming dictionary-based approaches, and matching or surpassing the performance of frontier AI models at a fraction of the cost. From 2019 to 2026, the share of postings that indicate new employees can work remotely at least one day per week rose more than ...
Working Paper
Artificial Intelligence and Inflation Forecasts
We explore the ability of Large Language Models (LLMs) to produce in-sample conditional inflation forecasts during the 2019-2023 period. We use a leading LLM (Google AI's PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years, and at almost all horizons. LLM forecasts exhibit slower reversion to the 2% inflation anchor.
Working Paper
Artificial Intelligence and Inflation Forecasts
We explore the ability of Large Language Models (LLMs) to produce conditional inflation forecasts during the 2019-2023 period. We use a leading LLM (Google AI's PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years, and at almost all horizons. LLM forecasts exhibit slower reversion to the 2% inflation anchor. We argue that this method of generating forecasts is inexpensive and can be ...