Large Language Models における意図的な性能制限

Detailed bibliographic record

Summary, etc.：: <p>Large Language Models (LLMs) possess the ability to perform well on unknown tasks and flexibly alter their behavior according to prompts. Leveragin...

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: Large Language Models における意図的な性能制限
Volume: JSAI2025
0
Author/Editor: 岩井皓暉
熊谷雄介
馬場雪乃
Author Heading: 岩井皓暉
IWAI Koki
熊谷雄介
KUMAGAE Yusuke
馬場雪乃
BABA Yukino
Publication Date: 2025
Publication Date (W3CDTF): 2025
Alternative Title: De-Tuning of Large 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: JSAI2025 0
Volume: JSAI2025
Issue: 0
Pages: 1M3OS47a05-1M3OS47a05
ISSN (Periodical Title): 2758-7347
Alias of Author: IWAI Koki
KUMAGAE Yusuke
BABA Yukino
Subject Heading: 大規模言語モデル
ベンチマーク
ペルソナ
ロールプレイ
Large Language Model
Benchmark
Persona
Role-Playing
Target Audience: 一般
DOI: 10.11517/pjsai.JSAI2025.0_1M3OS47a05
Access Restrictions: インターネット公開
Data Provider (Database): 科学技術振興機構 : J-STAGE
http://www.jstage.jst.go.jp