事前学習済み言語モデル中の多段階推論に関与するニューロンに関する分析

Detailed bibliographic record

Summary, etc.：: <p>Prompts have attracted attention as a way to exploit the performance of pre-trained language models, one of which is the chain-of-thought prompt. C...

Holdings of Libraries in Japan

This page shows libraries in Japan other than the National Diet Library that hold the material.

Please contact your local library for information on how to use materials or whether it is possible to request materials from the holding libraries.

other

You can check the details of this material, its authority (keywords that refer to materials on the same subject, author's name, etc.), etc.

Material Type: 記事
Title: 事前学習済み言語モデル中の多段階推論に関与するニューロンに関する分析
Volume: JSAI2023
0
Author/Editor: 沖村樹
岩澤有祐
小島武
松尾豊
Author Heading: OKIMURA Itsuki
沖村樹
IWASAWA Yusuke
岩澤有祐
KOJIMA Takeshi
小島武
MATSUO Yutaka
松尾豊
Publication Date: 2023
Publication Date (W3CDTF): 2023
Alternative Title: Analyzing Neurons Engaged in Multi-step Reasoning in Pre-trained Language Models
Periodical title: 人工知能学会全国大会論文集
Proceedings of the Annual Conference of JSAI
No. or year of volume/issue: JSAI2023 0
Volume: JSAI2023
Issue: 0
Pages: 2E4GS605-2E4GS605
ISSN (Periodical Title): 2758-7347
Alias of Author: OKIMURA Itsuki
IWASAWA Yusuke
KOJIMA Takeshi
MATSUO Yutaka
Subject Heading: multi-step reasoning
chain-of-thought
language model
多段階推論
思考連鎖
言語モデル
Target Audience: 一般
DOI: 10.11517/pjsai.JSAI2023.0_2E4GS605
Access Restrictions: インターネット公開
Data Provider (Database): 科学技術振興機構 : J-STAGE