國立虎尾科技大學 |

Exploring the Applications and Limitations of Large Language Models : = A Focus on ChatGPT in Virtual NPC Interactions.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Exploring the Applications and Limitations of Large Language Models :/
Reminder of title:	A Focus on ChatGPT in Virtual NPC Interactions.
Author:	Anand, Ayaan.
Description:	1 online resource (118 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-06.
Contained By:	Masters Abstracts International85-06.
Subject:	Design. -
Online resource:	click for full text (PQDT)
ISBN:	9798381162400

Exploring the Applications and Limitations of Large Language Models : = A Focus on ChatGPT in Virtual NPC Interactions.
Anand, Ayaan.

Exploring the Applications and Limitations of Large Language Models :A Focus on ChatGPT in Virtual NPC Interactions. - 1 online resource (118 pages)

Source: Masters Abstracts International, Volume: 85-06.

Thesis (M.S.)--Drexel University, 2023.

Includes bibliographical references

Large Language Models (LLMs), like ChatGPT and Google's Bard, have gained attention for their versatility and accessibility. This study delves into ChatGPT, exploring its potential to elevate virtual Non-Player Character (NPC) interactions, especially indomains such as law enforcement, mental health, and emergency services training. The primary goal was to assess ChatGPT's strengths and weaknesses through qualitative research, identifying opportunities for system enhancements. The evaluation criteriaen compass parameters vital to digital media storytelling, including empathy, emotional design, and interactive storytelling. By elucidating the capabilities and constraints of LLMs like ChatGPT and their role in enhancing virtual NPC interactions, this research aims to contribute valuable insights to domains reliant on human-computer interactions and emotional engagement. Additionally, the study integrates scenarios used in training police officers into the researched application, offering best practices for configuring an NPC powered by an LLM. While the emotional parameters showed overall success, there were occasional inconsistencies and unconventional responses. While testing the application for training in verbal de-escalation, the basic scenario seemed to work better than its moderate and complex counterparts due to the straightforward nature of the scenario and since it involved only two characters, making use of the basic techniques involved in learning verbal de-escalation.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381162400Subjects--Topical Terms:

595500
Design.
Subjects--Index Terms:

Emotional designIndex Terms--Genre/Form:

554714
Electronic books.

Exploring the Applications and Limitations of Large Language Models : = A Focus on ChatGPT in Virtual NPC Interactions.
LDR:02887ntm a22003977 4500 001 1144019
005 20240531084208.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381162400
035 $a (MiAaPQ)AAI30816362
035 $a AAI30816362
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Anand, Ayaan. $3 1468907
245 1 0 $a Exploring the Applications and Limitations of Large Language Models : $b A Focus on ChatGPT in Virtual NPC Interactions.
264 0 $c 2023
300 $a 1 online resource (118 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-06.
500 $a Advisor: Polyak, Emil.
502 $a Thesis (M.S.)--Drexel University, 2023.
504 $a Includes bibliographical references
520 $a Large Language Models (LLMs), like ChatGPT and Google's Bard, have gained attention for their versatility and accessibility. This study delves into ChatGPT, exploring its potential to elevate virtual Non-Player Character (NPC) interactions, especially indomains such as law enforcement, mental health, and emergency services training. The primary goal was to assess ChatGPT's strengths and weaknesses through qualitative research, identifying opportunities for system enhancements. The evaluation criteriaen compass parameters vital to digital media storytelling, including empathy, emotional design, and interactive storytelling. By elucidating the capabilities and constraints of LLMs like ChatGPT and their role in enhancing virtual NPC interactions, this research aims to contribute valuable insights to domains reliant on human-computer interactions and emotional engagement. Additionally, the study integrates scenarios used in training police officers into the researched application, offering best practices for configuring an NPC powered by an LLM. While the emotional parameters showed overall success, there were occasional inconsistencies and unconventional responses. While testing the application for training in verbal de-escalation, the basic scenario seemed to work better than its moderate and complex counterparts due to the straightforward nature of the scenario and since it involved only two characters, making use of the basic techniques involved in learning verbal de-escalation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Design. $3 595500
650 4 $a Film studies. $3 1179264
653 $a Emotional design
653 $a Empathy
653 $a Interactive storytelling
653 $a Large Language Models
653 $a Digital media
655 7 $a Electronic books. $2 local $3 554714
690 $a 0389
690 $a 0800
690 $a 0900
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Drexel University. $b Digital Media (Westphal College of Media Arts and Design). $3 1148571
773 0 $t Masters Abstracts International $g 85-06.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30816362 $z click for full text (PQDT)