Mitigating Interpretation Bias in Rock Records with Large Language Models: Insights from Paleoenvironmental Analysis

TL;DR

This paper presents a novel approach using Large Language Models with retrieval augmented generation to reduce interpretation bias in paleoenvironmental analysis, improving the accuracy of geological reconstructions.

Contribution

It introduces a systematic framework leveraging LLMs to generate and evaluate multiple hypotheses, mitigating human bias in rock record interpretation.

Findings

LLMs effectively generate multiple geological hypotheses.

The approach reduces interpretation bias in sedimentology and paleogeography.

Enhanced accuracy in paleoenvironmental reconstructions.

Abstract

The reconstruction of Earth's history faces significant challenges due to the nonunique interpretations often derived from rock records. The problem has long been recognized but there are no systematic solutions in practice. This study introduces an innovative approach that leverages Large Language Models (LLMs) along with retrieval augmented generation and real-time search capabilities to counteract interpretation biases, thereby enhancing the accuracy and reliability of geological analyses. By applying this framework to sedimentology and paleogeography, we demonstrate its effectiveness in mitigating interpretations biases through the generation and evaluation of multiple hypotheses for the same data, which can effectively reduce human bias. Our research illuminates the transformative potential of LLMs in refining paleoenvironmental studies and extends their applicability across various sub-disciplines of Earth sciences, enabling a deeper and more accurate depiction of Earth's evolution.