Saved in:
Bibliographic Details
Main Authors: Wang, Luoqi, Li, Haipeng, Hu, Linshu, Cai, Jiarui, Du, Zhenhong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.09977
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909255071694848
author Wang, Luoqi
Li, Haipeng
Hu, Linshu
Cai, Jiarui
Du, Zhenhong
author_facet Wang, Luoqi
Li, Haipeng
Hu, Linshu
Cai, Jiarui
Du, Zhenhong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mitigating Interpretation Bias in Rock Records with Large Language Models: Insights from Paleoenvironmental Analysis
Wang, Luoqi
Li, Haipeng
Hu, Linshu
Cai, Jiarui
Du, Zhenhong
Geophysics
Artificial Intelligence
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.
title Mitigating Interpretation Bias in Rock Records with Large Language Models: Insights from Paleoenvironmental Analysis
topic Geophysics
Artificial Intelligence
url https://arxiv.org/abs/2407.09977