Safe Generative Chats in a WhatsApp Intelligent Tutoring System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Levonian, Zachary, Henkel, Owen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914859923275776
author Levonian, Zachary
Henkel, Owen
author_facet Levonian, Zachary
Henkel, Owen
contents Large language models (LLMs) are flexible, personalizable, and available, which makes their use within Intelligent Tutoring Systems (ITSs) appealing. However, that flexibility creates risks: inaccuracies, harmful content, and non-curricular material. Ethically deploying LLM-backed ITS systems requires designing safeguards that ensure positive experiences for students. We describe the design of a conversational system integrated into an ITS, and our experience evaluating its safety with red-teaming, an in-classroom usability test, and field deployment. We present empirical data from more than 8,000 student conversations with this system, finding that GPT-3.5 rarely generates inappropriate messages. Comparatively more common is inappropriate messages from students, which prompts us to reason about safeguarding as a content moderation and classroom management problem. The student interaction behaviors we observe provide implications for designers - to focus on student inputs as a content moderation problem - and implications for researchers - to focus on subtle forms of bad content.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Safe Generative Chats in a WhatsApp Intelligent Tutoring System
Levonian, Zachary
Henkel, Owen
Human-Computer Interaction
Large language models (LLMs) are flexible, personalizable, and available, which makes their use within Intelligent Tutoring Systems (ITSs) appealing. However, that flexibility creates risks: inaccuracies, harmful content, and non-curricular material. Ethically deploying LLM-backed ITS systems requires designing safeguards that ensure positive experiences for students. We describe the design of a conversational system integrated into an ITS, and our experience evaluating its safety with red-teaming, an in-classroom usability test, and field deployment. We present empirical data from more than 8,000 student conversations with this system, finding that GPT-3.5 rarely generates inappropriate messages. Comparatively more common is inappropriate messages from students, which prompts us to reason about safeguarding as a content moderation and classroom management problem. The student interaction behaviors we observe provide implications for designers - to focus on student inputs as a content moderation problem - and implications for researchers - to focus on subtle forms of bad content.
title Safe Generative Chats in a WhatsApp Intelligent Tutoring System
topic Human-Computer Interaction
url https://arxiv.org/abs/2407.04915