國立虎尾科技大學 |

Enhancing the Comprehension : = Text Simplification Approaches and the Role of Large Language Models.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Enhancing the Comprehension :/
Reminder of title:	Text Simplification Approaches and the Role of Large Language Models.
Author:	Yang, Ziyu.
Description:	1 online resource (81 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798382757445

Enhancing the Comprehension : = Text Simplification Approaches and the Role of Large Language Models.
Yang, Ziyu.

Enhancing the Comprehension :Text Simplification Approaches and the Role of Large Language Models. - 1 online resource (81 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

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

Includes bibliographical references

Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. There has been an increasing interest in directly sharing radiology reports with patients to improve doctor-patient communication. However, radiology reports are primarily created for communication of imaging findings among medical professionals and are difficult to comprehend by laypeople. Thus, it would be useful if a patient-friendly version of a radiology report could be provided to patients in addition to the original report. Addressing this gap by creating patient-friendly versions of these reports not only enhances doctor-patient communication but also empowers patients by providing them with accessible information about their health conditions. However, a conundrum arises as requiring radiologists to augment traditional reports with patient-friendly summaries could exert negative influence on their cognitive load and productivity. Recent research worked on automatic simplification of health records, employing both lexical and semantic simplification methods, with recent advancements incorporating deep learning techniques. Yet, training these deep learning models for medical text simplification necessitates the collection of costly labeled data.To address these challenges, we investigate the roles of Large Language Models (LLMs) in simplifying radiology reports to make them more accessible to patients. Firstly, we assess GPT-3's capacity to generate patient-friendly summaries of radiology sentences, specifically focusing on liver conditions. Our findings reveal that with appropriate prompting and finetuning, GPT-3 can produce high-quality simplifications, as evidenced by both automated metrics and manual evaluations by radiologists. Secondly, addressing the challenge of data scarcity in training models for medical text simplification, we introduce a novel data augmentation strategy. This approach leverages the generative capabilities of pre-trained LLMs to create simplified versions of unlabeled radiology sentences and employs paraphrasing techniques on labeled data, significantly enhancing the accuracy of our fine-tuned simplification model beyond baseline methods. Lastly, we explore the effectiveness of advanced prompting mechanisms, such as chain-of-thought and self-correction, in improving the quality of text simplifications. Through a dual-evaluation protocol involving both radiologists and laypeople, we demonstrate the superiority of self-correction prompting in producing simplifications that are both factually accurate and easier for laypeople to understand. Collectively, these studies underscore the potential of LLMs in bridging the gap between complex medical information and patient comprehension, providing valuable insights into the methodologies and evaluation frameworks that can facilitate the development of more accessible health communication tools.

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

Mode of access: World Wide Web

ISBN: 9798382757445Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Large Language ModelsIndex Terms--Genre/Form:

554714
Electronic books.

Enhancing the Comprehension : = Text Simplification Approaches and the Role of Large Language Models.
LDR:04331ntm a22003977 4500 001 1144992
005 20240617111735.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382757445
035 $a (MiAaPQ)AAI31149360
035 $a AAI31149360
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Yang, Ziyu. $3 1470187
245 1 0 $a Enhancing the Comprehension : $b Text Simplification Approaches and the Role of Large Language Models.
264 0 $c 2024
300 $a 1 online resource (81 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: 85-11, Section: B.
500 $a Advisor: Vucetic, Slobodan.
502 $a Thesis (Ph.D.)--Temple University, 2024.
504 $a Includes bibliographical references
520 $a Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. There has been an increasing interest in directly sharing radiology reports with patients to improve doctor-patient communication. However, radiology reports are primarily created for communication of imaging findings among medical professionals and are difficult to comprehend by laypeople. Thus, it would be useful if a patient-friendly version of a radiology report could be provided to patients in addition to the original report. Addressing this gap by creating patient-friendly versions of these reports not only enhances doctor-patient communication but also empowers patients by providing them with accessible information about their health conditions. However, a conundrum arises as requiring radiologists to augment traditional reports with patient-friendly summaries could exert negative influence on their cognitive load and productivity. Recent research worked on automatic simplification of health records, employing both lexical and semantic simplification methods, with recent advancements incorporating deep learning techniques. Yet, training these deep learning models for medical text simplification necessitates the collection of costly labeled data.To address these challenges, we investigate the roles of Large Language Models (LLMs) in simplifying radiology reports to make them more accessible to patients. Firstly, we assess GPT-3's capacity to generate patient-friendly summaries of radiology sentences, specifically focusing on liver conditions. Our findings reveal that with appropriate prompting and finetuning, GPT-3 can produce high-quality simplifications, as evidenced by both automated metrics and manual evaluations by radiologists. Secondly, addressing the challenge of data scarcity in training models for medical text simplification, we introduce a novel data augmentation strategy. This approach leverages the generative capabilities of pre-trained LLMs to create simplified versions of unlabeled radiology sentences and employs paraphrasing techniques on labeled data, significantly enhancing the accuracy of our fine-tuned simplification model beyond baseline methods. Lastly, we explore the effectiveness of advanced prompting mechanisms, such as chain-of-thought and self-correction, in improving the quality of text simplifications. Through a dual-evaluation protocol involving both radiologists and laypeople, we demonstrate the superiority of self-correction prompting in producing simplifications that are both factually accurate and easier for laypeople to understand. Collectively, these studies underscore the potential of LLMs in bridging the gap between complex medical information and patient comprehension, providing valuable insights into the methodologies and evaluation frameworks that can facilitate the development of more accessible health communication tools.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
650 4 $a Biomedical engineering. $3 588770
653 $a Large Language Models
653 $a Radiology
653 $a Doctor-patient communication
653 $a Deep learning techniques
653 $a Health records
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0541
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Temple University. $b Computer and Information Science. $3 1182490
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31149360 $z click for full text (PQDT)