Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cohn, Clayton, Snyder, Caitlin, Montenegro, Justin, Biswas, Gautam
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914855488847872
author Cohn, Clayton
Snyder, Caitlin
Montenegro, Justin
Biswas, Gautam
author_facet Cohn, Clayton
Snyder, Caitlin
Montenegro, Justin
Biswas, Gautam
contents LLMs have demonstrated proficiency in contextualizing their outputs using human input, often matching or beating human-level performance on a variety of tasks. However, LLMs have not yet been used to characterize synergistic learning in students' collaborative discourse. In this exploratory work, we take a first step towards adopting a human-in-the-loop prompt engineering approach with GPT-4-Turbo to summarize and categorize students' synergistic learning during collaborative discourse. Our preliminary findings suggest GPT-4-Turbo may be able to characterize students' synergistic learning in a manner comparable to humans and that our approach warrants further investigation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03677
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis
Cohn, Clayton
Snyder, Caitlin
Montenegro, Justin
Biswas, Gautam
Computation and Language
LLMs have demonstrated proficiency in contextualizing their outputs using human input, often matching or beating human-level performance on a variety of tasks. However, LLMs have not yet been used to characterize synergistic learning in students' collaborative discourse. In this exploratory work, we take a first step towards adopting a human-in-the-loop prompt engineering approach with GPT-4-Turbo to summarize and categorize students' synergistic learning during collaborative discourse. Our preliminary findings suggest GPT-4-Turbo may be able to characterize students' synergistic learning in a manner comparable to humans and that our approach warrants further investigation.
title Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis
topic Computation and Language
url https://arxiv.org/abs/2405.03677