Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahad, Jawad Ibn, Sultan, Rafeed Mohammad, Kaikobad, Abraham, Rahman, Fuad, Amin, Mohammad Ruhul, Mohammed, Nabeel, Rahman, Shafin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916485498142720
author Ahad, Jawad Ibn
Sultan, Rafeed Mohammad
Kaikobad, Abraham
Rahman, Fuad
Amin, Mohammad Ruhul
Mohammed, Nabeel
Rahman, Shafin
author_facet Ahad, Jawad Ibn
Sultan, Rafeed Mohammad
Kaikobad, Abraham
Rahman, Fuad
Amin, Mohammad Ruhul
Mohammed, Nabeel
Rahman, Shafin
contents This study investigates the automation of meta-analysis in scientific documents using large language models (LLMs). Meta-analysis is a robust statistical method that synthesizes the findings of multiple studies support articles to provide a comprehensive understanding. We know that a meta-article provides a structured analysis of several articles. However, conducting meta-analysis by hand is labor-intensive, time-consuming, and susceptible to human error, highlighting the need for automated pipelines to streamline the process. Our research introduces a novel approach that fine-tunes the LLM on extensive scientific datasets to address challenges in big data handling and structured data extraction. We automate and optimize the meta-analysis process by integrating Retrieval Augmented Generation (RAG). Tailored through prompt engineering and a new loss metric, Inverse Cosine Distance (ICD), designed for fine-tuning on large contextual datasets, LLMs efficiently generate structured meta-analysis content. Human evaluation then assesses relevance and provides information on model performance in key metrics. This research demonstrates that fine-tuned models outperform non-fine-tuned models, with fine-tuned LLMs generating 87.6% relevant meta-analysis abstracts. The relevance of the context, based on human evaluation, shows a reduction in irrelevancy from 4.56% to 1.9%. These experiments were conducted in a low-resource environment, highlighting the study's contribution to enhancing the efficiency and reliability of meta-analysis automation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10878
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis
Ahad, Jawad Ibn
Sultan, Rafeed Mohammad
Kaikobad, Abraham
Rahman, Fuad
Amin, Mohammad Ruhul
Mohammed, Nabeel
Rahman, Shafin
Computation and Language
Artificial Intelligence
Information Retrieval
This study investigates the automation of meta-analysis in scientific documents using large language models (LLMs). Meta-analysis is a robust statistical method that synthesizes the findings of multiple studies support articles to provide a comprehensive understanding. We know that a meta-article provides a structured analysis of several articles. However, conducting meta-analysis by hand is labor-intensive, time-consuming, and susceptible to human error, highlighting the need for automated pipelines to streamline the process. Our research introduces a novel approach that fine-tunes the LLM on extensive scientific datasets to address challenges in big data handling and structured data extraction. We automate and optimize the meta-analysis process by integrating Retrieval Augmented Generation (RAG). Tailored through prompt engineering and a new loss metric, Inverse Cosine Distance (ICD), designed for fine-tuning on large contextual datasets, LLMs efficiently generate structured meta-analysis content. Human evaluation then assesses relevance and provides information on model performance in key metrics. This research demonstrates that fine-tuned models outperform non-fine-tuned models, with fine-tuned LLMs generating 87.6% relevant meta-analysis abstracts. The relevance of the context, based on human evaluation, shows a reduction in irrelevancy from 4.56% to 1.9%. These experiments were conducted in a low-resource environment, highlighting the study's contribution to enhancing the efficiency and reliability of meta-analysis automation.
title Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2411.10878