國立虎尾科技大學 |

Controlling Long-Form Large Language Model Outputs.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Controlling Long-Form Large Language Model Outputs./
作者:	Yang, Kevin.
面頁冊數:	1 online resource (106 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
Contained By:	Dissertations Abstracts International85-09B.
標題:	Computer engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798381851991

Controlling Long-Form Large Language Model Outputs.
Yang, Kevin.

Controlling Long-Form Large Language Model Outputs. - 1 online resource (106 pages)

Source: Dissertations Abstracts International, Volume: 85-09, Section: B.

Thesis (Ph.D.)--University of California, Berkeley, 2023.

Includes bibliographical references

As large language models have greatly increased in capability in recent years, it becomes increasingly important to improve our ability to exert control over their outputs. In this thesis, I discuss several such control schemes I have developed, ranging from pure inference-time control to finetuning-based alignment methods. I will first discuss highly general methods that apply to unstructured natural language generation, including both an inference-time control scheme called FUDGE as well as a reinforcement-learning based finetuning approach called RLCD. I will next discuss more specialized methods that can be used for control in more structured domains such as molecule design, program synthesis, and semantic parsing. Finally, I will show how many of these ideas can be used in conjunction with structured planning via prompting to extend our control to much longer outputs-in the range of thousands of words-in an automatic story generation application.

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

Mode of access: World Wide Web

ISBN: 9798381851991Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Language modelsIndex Terms--Genre/Form:

554714
Electronic books.

Controlling Long-Form Large Language Model Outputs.
LDR:02300ntm a22003857 4500 001 1146419
005 20240812064611.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381851991
035 $a (MiAaPQ)AAI30814534
035 $a AAI30814534
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Yang, Kevin. $3 1471807
245 1 0 $a Controlling Long-Form Large Language Model Outputs.
264 0 $c 2023
300 $a 1 online resource (106 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: 85-09, Section: B.
500 $a Advisor: Klein, Dan.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2023.
504 $a Includes bibliographical references
520 $a As large language models have greatly increased in capability in recent years, it becomes increasingly important to improve our ability to exert control over their outputs. In this thesis, I discuss several such control schemes I have developed, ranging from pure inference-time control to finetuning-based alignment methods. I will first discuss highly general methods that apply to unstructured natural language generation, including both an inference-time control scheme called FUDGE as well as a reinforcement-learning based finetuning approach called RLCD. I will next discuss more specialized methods that can be used for control in more structured domains such as molecule design, program synthesis, and semantic parsing. Finally, I will show how many of these ideas can be used in conjunction with structured planning via prompting to extend our control to much longer outputs-in the range of thousands of words-in an automatic story generation application.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Computer science. $3 573171
653 $a Language models
653 $a Story generation
653 $a Inference-time control
653 $a Reinforcement-learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Computer Science. $3 1179511
773 0 $t Dissertations Abstracts International $g 85-09B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30814534 $z click for full text (PQDT)