De-jargonizing Science for Journalists with GPT-4: A Pilot Study

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nishal, Sachita, Lee, Eric, Diakopoulos, Nicholas
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929544930263040
author Nishal, Sachita
Lee, Eric
Diakopoulos, Nicholas
author_facet Nishal, Sachita
Lee, Eric
Diakopoulos, Nicholas
contents This study offers an initial evaluation of a human-in-the-loop system leveraging GPT-4 (a large language model or LLM), and Retrieval-Augmented Generation (RAG) to identify and define jargon terms in scientific abstracts, based on readers' self-reported knowledge. The system achieves fairly high recall in identifying jargon and preserves relative differences in readers' jargon identification, suggesting personalization as a feasible use-case for LLMs to support sense-making of complex information. Surprisingly, using only abstracts for context to generate definitions yields slightly more accurate and higher quality definitions than using RAG-based context from the fulltext of an article. The findings highlight the potential of generative AI for assisting science reporters, and can inform future work on developing tools to simplify dense documents.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle De-jargonizing Science for Journalists with GPT-4: A Pilot Study
Nishal, Sachita
Lee, Eric
Diakopoulos, Nicholas
Computation and Language
Computers and Society
Human-Computer Interaction
H.4; H.5
This study offers an initial evaluation of a human-in-the-loop system leveraging GPT-4 (a large language model or LLM), and Retrieval-Augmented Generation (RAG) to identify and define jargon terms in scientific abstracts, based on readers' self-reported knowledge. The system achieves fairly high recall in identifying jargon and preserves relative differences in readers' jargon identification, suggesting personalization as a feasible use-case for LLMs to support sense-making of complex information. Surprisingly, using only abstracts for context to generate definitions yields slightly more accurate and higher quality definitions than using RAG-based context from the fulltext of an article. The findings highlight the potential of generative AI for assisting science reporters, and can inform future work on developing tools to simplify dense documents.
title De-jargonizing Science for Journalists with GPT-4: A Pilot Study
topic Computation and Language
Computers and Society
Human-Computer Interaction
H.4; H.5
url https://arxiv.org/abs/2410.12069