東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Designing and Evaluating Language Mo...

Lee, Mina.

FindBook

Google Book

Amazon

博客來

Designing and Evaluating Language Models for Human Interaction.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Designing and Evaluating Language Models for Human Interaction./
作者:	Lee, Mina.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	135 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
標題:	Writing. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615211
ISBN:	9798380482509

Designing and Evaluating Language Models for Human Interaction.
Lee, Mina.

Designing and Evaluating Language Models for Human Interaction. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 135 p.

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--Stanford University, 2023.

Despite the ubiquity of language models (LMs) in real-world applications (e.g., web search, text autocomplete, and content generation), most LMs are not optimized for, nor are they evaluated on, real-world usage where human users interact with LMs. To address this gap, this dissertation focuses on designing and evaluating LMs for human interaction. We first start by focusing on one specific need that writers encounter in the revision process: coming up with content given surrounding context. To support this need, we propose a training method to enable any pre-trained LMs to accomplish the task of filling in the blanks, helping to better facilitate human-LM interaction. Second, we build a platform, CoAuthor, to capture human-LM interaction as interaction traces. With CoAuthor, we demonstrate how collecting a large interaction dataset and analyzing the traces provide unique insights into LM capabilities regarding language, ideation, and collaboration in human-LM interaction. Lastly, we propose a new evaluation framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and metrics for human-LM interaction tasks beyond writing. Finally, we discuss open challenges and future directions in this field.

ISBN: 9798380482509Subjects--Topical Terms:

551664
Writing.

Designing and Evaluating Language Models for Human Interaction.
LDR:02316nmm a2200337 4500 001 2398306
005 20240812064606.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380482509
035 $a (MiAaPQ)AAI30615211
035 $a (MiAaPQ)STANFORDrj262yf1528
035 $a AAI30615211
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lee, Mina. $3 3768221
245 1 0 $a Designing and Evaluating Language Models for Human Interaction.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 135 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Liang, Percy;Bernstein, Michael S;Yang, Qian.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
520 $a Despite the ubiquity of language models (LMs) in real-world applications (e.g., web search, text autocomplete, and content generation), most LMs are not optimized for, nor are they evaluated on, real-world usage where human users interact with LMs. To address this gap, this dissertation focuses on designing and evaluating LMs for human interaction. We first start by focusing on one specific need that writers encounter in the revision process: coming up with content given surrounding context. To support this need, we propose a training method to enable any pre-trained LMs to accomplish the task of filling in the blanks, helping to better facilitate human-LM interaction. Second, we build a platform, CoAuthor, to capture human-LM interaction as interaction traces. With CoAuthor, we demonstrate how collecting a large interaction dataset and analyzing the traces provide unique insights into LM capabilities regarding language, ideation, and collaboration in human-LM interaction. Lastly, we propose a new evaluation framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and metrics for human-LM interaction tasks beyond writing. Finally, we discuss open challenges and future directions in this field.
590 $a School code: 0212.
650 4 $a Writing. $3 551664
650 4 $a Communication. $3 524709
650 4 $a Input output. $3 3686610
650 4 $a Neural networks. $3 677449
650 4 $a Design. $3 518875
650 4 $a Natural language processing. $3 1073412
650 4 $a Creativity. $3 605632
650 4 $a Human-computer interaction. $3 560071
650 4 $a Designers. $3 589292
690 $a 0389
690 $a 0459
690 $a 0800
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 85-04B.
790 $a 0212
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615211