Saved in:
Bibliographic Details
Main Authors: Kubota, So, Yakura, Hiromu, Coavoux, Samuel, Yamada, Sho, Nakamura, Yuki
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918349475151872
author Kubota, So
Yakura, Hiromu
Coavoux, Samuel
Yamada, Sho
Nakamura, Yuki
author_facet Kubota, So
Yakura, Hiromu
Coavoux, Samuel
Yamada, Sho
Nakamura, Yuki
contents The replication crisis, the failure of scientific claims to be validated by further research, is one of the most pressing issues for empirical research. This is partly an incentive problem: replication is costly and less well rewarded than original research. Large language models (LLMs) have accelerated scientific production by streamlining writing, coding, and reviewing, yet this acceleration risks outpacing verification. To address this, we present an LLM-based system that replicates statistical analyses from social science papers and flags potential problems. Quantitative social science is particularly well-suited to automation because it relies on standard statistical models, shared public datasets, and uniform reporting formats such as regression tables and summary statistics. We present a prototype that iterates LLM-based text interpretation, code generation, execution, and discrepancy analysis, demonstrating its capabilities by reproducing key results from a seminal sociology paper. We also outline application scenarios including pre-submission checks, peer-review support, and meta-scientific audits, positioning AI verification as assistive infrastructure that strengthens research integrity.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18453
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM-Assisted Replication for Quantitative Social Science
Kubota, So
Yakura, Hiromu
Coavoux, Samuel
Yamada, Sho
Nakamura, Yuki
Computers and Society
Artificial Intelligence
The replication crisis, the failure of scientific claims to be validated by further research, is one of the most pressing issues for empirical research. This is partly an incentive problem: replication is costly and less well rewarded than original research. Large language models (LLMs) have accelerated scientific production by streamlining writing, coding, and reviewing, yet this acceleration risks outpacing verification. To address this, we present an LLM-based system that replicates statistical analyses from social science papers and flags potential problems. Quantitative social science is particularly well-suited to automation because it relies on standard statistical models, shared public datasets, and uniform reporting formats such as regression tables and summary statistics. We present a prototype that iterates LLM-based text interpretation, code generation, execution, and discrepancy analysis, demonstrating its capabilities by reproducing key results from a seminal sociology paper. We also outline application scenarios including pre-submission checks, peer-review support, and meta-scientific audits, positioning AI verification as assistive infrastructure that strengthens research integrity.
title LLM-Assisted Replication for Quantitative Social Science
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2602.18453