國立虎尾科技大學 |

Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support./
Author:	Chakrabarty, Tuhin.
Description:	1 online resource (234 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
Contained By:	Dissertations Abstracts International86-02B.
Subject:	Linguistics. -
Online resource:	click for full text (PQDT)
ISBN:	9798383588550

Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support.
Chakrabarty, Tuhin.

Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support. - 1 online resource (234 pages)

Source: Dissertations Abstracts International, Volume: 86-02, Section: B.

Thesis (Ph.D.)--Columbia University, 2024.

Includes bibliographical references

Large language models (LLMs) constitute a paradigm shift in Natural Language Processing and Artificial Intelligence. In this thesis, I explore the integration of creative capabilities into artificial intelligence systems to enhance their interaction with humans. I discuss the necessity of equipping AI with the ability to comprehend and generate content that transcends the literal, capturing the subtleties of human art and conversation. To address the limitations of current state-of-the-art AI models in creativity, in this thesis I first present a methodology for developing unsupervised or weakly-supervised machine learning models that incorporate implicit/commonsense knowledge. This approach enables the generation of creative textual content, such as sarcasm and metaphors, by leveraging external sources of commonsense knowledge. Furthermore, I discuss the challenges of collecting large-scale, high-quality datasets for training AI in creative tasks and propose collaborative efforts between expert humans and state-of-the-art models to overcome these obstacles. Finally, I advocate for human-centered robust evaluation protocols and show how to design and develop such protocols so that we can better assess the quality of model outputs for creativity in both standalone and interactive settings. I end this thesis by highlighting the current limitations of existing models and future directions toward building better models that will enable efficient and trustworthy human-AI collaboration systems.

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

Mode of access: World Wide Web

ISBN: 9798383588550Subjects--Topical Terms:

557829
Linguistics.
Subjects--Index Terms:

Large language modelsIndex Terms--Genre/Form:

554714
Electronic books.

Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support.
LDR:02935ntm a22004097 4500 001 1150907
005 20241029122352.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383588550
035 $a (MiAaPQ)AAI31299606
035 $a AAI31299606
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Chakrabarty, Tuhin. $3 1477536
245 1 0 $a Knowledge-Enhanced Large Language Models and Human-AI Collaboration Frameworks for Creativity Support.
264 0 $c 2024
300 $a 1 online resource (234 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: Dissertations Abstracts International, Volume: 86-02, Section: B.
500 $a Advisor: Muresan, Smaranda.
502 $a Thesis (Ph.D.)--Columbia University, 2024.
504 $a Includes bibliographical references
520 $a Large language models (LLMs) constitute a paradigm shift in Natural Language Processing and Artificial Intelligence. In this thesis, I explore the integration of creative capabilities into artificial intelligence systems to enhance their interaction with humans. I discuss the necessity of equipping AI with the ability to comprehend and generate content that transcends the literal, capturing the subtleties of human art and conversation. To address the limitations of current state-of-the-art AI models in creativity, in this thesis I first present a methodology for developing unsupervised or weakly-supervised machine learning models that incorporate implicit/commonsense knowledge. This approach enables the generation of creative textual content, such as sarcasm and metaphors, by leveraging external sources of commonsense knowledge. Furthermore, I discuss the challenges of collecting large-scale, high-quality datasets for training AI in creative tasks and propose collaborative efforts between expert humans and state-of-the-art models to overcome these obstacles. Finally, I advocate for human-centered robust evaluation protocols and show how to design and develop such protocols so that we can better assess the quality of model outputs for creativity in both standalone and interactive settings. I end this thesis by highlighting the current limitations of existing models and future directions toward building better models that will enable efficient and trustworthy human-AI collaboration systems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Linguistics. $3 557829
650 4 $a Computer science. $3 573171
650 4 $a Language. $3 571568
653 $a Large language models
653 $a AI models
653 $a State-of-the-art
653 $a Creative tasks
653 $a High-quality datasets
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0290
690 $a 0984
690 $a 0679
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Columbia University. $b Computer Science. $3 1179509
773 0 $t Dissertations Abstracts International $g 86-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31299606 $z click for full text (PQDT)