Large Language Models as Evaluators for Scientific Synthesis

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Evans, Julia, D'Souza, Jennifer, Auer, Sören
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914857502113792
author Evans, Julia
D'Souza, Jennifer
Auer, Sören
author_facet Evans, Julia
D'Souza, Jennifer
Auer, Sören
contents Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations to those of human annotators. We used a dataset of 100 research questions and their syntheses made by GPT-4 from abstracts of five related papers, checked against human quality ratings. The study evaluates both the closed-source GPT-4 and the open-source Mistral model's ability to rate these summaries and provide reasons for their judgments. Preliminary results show that LLMs can offer logical explanations that somewhat match the quality ratings, yet a deeper statistical analysis shows a weak correlation between LLM and human ratings, suggesting the potential and current limitations of LLMs in scientific synthesis evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models as Evaluators for Scientific Synthesis
Evans, Julia
D'Souza, Jennifer
Auer, Sören
Computation and Language
Artificial Intelligence
Information Theory
Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations to those of human annotators. We used a dataset of 100 research questions and their syntheses made by GPT-4 from abstracts of five related papers, checked against human quality ratings. The study evaluates both the closed-source GPT-4 and the open-source Mistral model's ability to rate these summaries and provide reasons for their judgments. Preliminary results show that LLMs can offer logical explanations that somewhat match the quality ratings, yet a deeper statistical analysis shows a weak correlation between LLM and human ratings, suggesting the potential and current limitations of LLMs in scientific synthesis evaluation.
title Large Language Models as Evaluators for Scientific Synthesis
topic Computation and Language
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2407.02977