國立虎尾科技大學 |

Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction : = A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction :/
其他題名:	A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying.
作者:	Ghali, Mohammed-Khalil.
面頁冊數:	1 online resource (115 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Systems science. -
電子資源:	click for full text (PQDT)
ISBN:	9798383098448

Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction : = A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying.
Ghali, Mohammed-Khalil.

Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction :A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying. - 1 online resource (115 pages)

Source: Masters Abstracts International, Volume: 85-12.

Thesis (M.S.)--State University of New York at Binghamton, 2024.

Includes bibliographical references

With the exponential growth of data, the demand for skilled AI practitioners has increased. Large Language Models (LLMs) have come to help overcome this problem, but they still struggle with domain-specific data, extracting named entities in unconstrained environments, and dealing with limited context windows. The aim is to develop wrapper models on top of LLMs that transcend these barriers. These proposed multi-field models undergo rigorous evaluation to ensure they deliver state-of-the-art solutions. The proposed information retrieval model, SOLARIS, demonstrated outstanding performance, achieving a Rouge-L F1 score of 0.93 and 0.98 in two distinct evaluation datasets, establishing itself as a state-of-the-art (SOTA) solution for these datasets. Similarly, MedSafeX, our proposed named entity extractor attained a Rouge-L F1 score of 0.98 in one of the evaluation datasets. Additionally, DBCopilot, the large database querying framework, showcased its efficiency in SQL querying with an Execution accuracy (EX) of 0.82 and an Exact-Set-Match (EM) accuracy of 0.60 across the Spider dataset, underlining its potential for improving and automating database querying tasks. This abstract outlines pioneering efforts in leveraging Generative AI and In-Context Learning to transform human-text interaction. The goal is to redefine the landscape of Generative AI utilization, making it more accessible to all through its democratization.

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

Mode of access: World Wide Web

ISBN: 9798383098448Subjects--Topical Terms:

1148479
Systems science.
Subjects--Index Terms:

Large Language ModelsIndex Terms--Genre/Form:

554714
Electronic books.

Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction : = A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying.
LDR:02907ntm a22003977 4500 001 1150197
005 20241022111612.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383098448
035 $a (MiAaPQ)AAI31295623
035 $a AAI31295623
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ghali, Mohammed-Khalil. $3 1476638
245 1 0 $a Leveraging Generative AI and in Context Learning to Reshape Human-Text Interaction : $b A Novel Paradigm for Information Retrieval, Named Entities Extraction, and Database Querying.
264 0 $c 2024
300 $a 1 online resource (115 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: 85-12.
500 $a Advisor: Jin, Yu.
502 $a Thesis (M.S.)--State University of New York at Binghamton, 2024.
504 $a Includes bibliographical references
520 $a With the exponential growth of data, the demand for skilled AI practitioners has increased. Large Language Models (LLMs) have come to help overcome this problem, but they still struggle with domain-specific data, extracting named entities in unconstrained environments, and dealing with limited context windows. The aim is to develop wrapper models on top of LLMs that transcend these barriers. These proposed multi-field models undergo rigorous evaluation to ensure they deliver state-of-the-art solutions. The proposed information retrieval model, SOLARIS, demonstrated outstanding performance, achieving a Rouge-L F1 score of 0.93 and 0.98 in two distinct evaluation datasets, establishing itself as a state-of-the-art (SOTA) solution for these datasets. Similarly, MedSafeX, our proposed named entity extractor attained a Rouge-L F1 score of 0.98 in one of the evaluation datasets. Additionally, DBCopilot, the large database querying framework, showcased its efficiency in SQL querying with an Execution accuracy (EX) of 0.82 and an Exact-Set-Match (EM) accuracy of 0.60 across the Spider dataset, underlining its potential for improving and automating database querying tasks. This abstract outlines pioneering efforts in leveraging Generative AI and In-Context Learning to transform human-text interaction. The goal is to redefine the landscape of Generative AI utilization, making it more accessible to all through its democratization.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Systems science. $3 1148479
650 4 $a Engineering. $3 561152
650 4 $a Industrial engineering. $3 679492
653 $a Large Language Models
653 $a Prompt engineering
653 $a Exact-Set-Match
653 $a Human-text interaction
655 7 $a Electronic books. $2 local $3 554714
690 $a 0546
690 $a 0800
690 $a 0537
690 $a 0790
710 2 $a State University of New York at Binghamton. $b Systems Science Industrial Engineering. $3 1182293
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31295623 $z click for full text (PQDT)