Evaluating Large Language Model Capabilities in Assessing Spatial Econometrics Research

TL;DR

This study evaluates the ability of Large Language Models to assess the economic validity and consistency of spatial econometrics research, highlighting their strengths and limitations in peer review support.

Contribution

It introduces a novel evaluation framework for LLMs in assessing economic research quality, focusing on spatial econometrics papers and their counterfactual summaries.

Findings

LLMs excel at assessing variable choice coherence (F1 score 0.87).

Performance varies on deeper assessments like coefficient plausibility.

Model choice and paper characteristics significantly affect evaluation accuracy.

Abstract

This paper investigates Large Language Models (LLMs) ability to assess the economic soundness and theoretical consistency of empirical findings in spatial econometrics. We created original and deliberately altered "counterfactual" summaries from 28 published papers (2005-2024), which were evaluated by a diverse set of LLMs. The LLMs provided qualitative assessments and structured binary classifications on variable choice, coefficient plausibility, and publication suitability. The results indicate that while LLMs can expertly assess the coherence of variable choices (with top models like GPT-4o achieving an overall F1 score of 0.87), their performance varies significantly when evaluating deeper aspects such as coefficient plausibility and overall publication suitability. The results further revealed that the choice of LLM, the specific characteristics of the paper and the interaction between these two factors significantly influence the accuracy of the assessment, particularly for nuanced judgments. These findings highlight LLMs' current strengths in assisting with initial, more surface-level checks and their limitations in performing comprehensive, deep economic reasoning, suggesting a potential assistive role in peer review that still necessitates robust human oversight.