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

Sachita Nishal, Eric Lee, Nicholas Diakopoulos
10/15/2024
cs.CLcs.CYcs.HC

No official code found. Best implementation: ericlee878/ScienceDeJargonizer (1 star, last commit 2024-06-01).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

ericlee878/ScienceDeJargonizerCommunity100%

ScienceDeJargonizer simplifies scientific jargon for journalists without scientific backgrounds, using LLMs . This tool transforms complex terms into clear explanations, aiding accurate and accessible science reporting.

10CSS, HTMLApr 3, 20242 years ago

Similar Papers

Large Language Models for Scientific Information Extraction: An Empirical Study for Virology

83% match2024

From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science

82% match2024

FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article

80% match1 repo2025

SciGPT: A Large Language Model for Scientific Literature Understanding and Knowledge Discovery

80% match2025

AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment

80% match2024

LLMs as Science Journalists: Supporting Early-stage Researchers in Communicating Their Science to the Public

80% match2026

Cite this paper

@article{nishal2024dejargonizing,
  title  = {De-jargonizing Science for Journalists with GPT-4: A Pilot Study},
  author = {Sachita Nishal and Eric Lee and Nicholas Diakopoulos},
  year   = {2024},
  eprint = {2410.12069},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.12069v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.12069.svg)](https://codeofpaper.com/paper/2410.12069)

Discussion