logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Evaluating LLM Performance in TRIZ-Based System Forecasting: A Study Using 9-Windows

delete2026-01-01
delete0
PRE
AI
M
Mélusine Caillard *
G
Giacomo Bersano
G
Gaston Opler
P
Pierre-Emmanuel Fayemi
DOI：10.1007/978-3-032-08847-5_8delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Large language models (LLMs) show promise for structured foresight tasks but struggle with coherence and methodological consistency. This study assesses seven LLMs in generating TRIZ system operator tools (SOTs) across five systems and three prompt types. Performance drops in complex or vague contexts, especially in trend and supersystem areas. Expert reviews and semantic metrics show that breaking down prompts improves output quality. Findings suggest current LLMs need human-AI collaboration and tailored prompting for advanced foresight.
Keywords:
LLM
Data-driven TRIZ
Technology forecasting

Journal

W
WORLD CONFERENCE OF AI-POWERED INNOVATION AND TRIZ METHODOLOGY, TRAI 2025, PT I
IF:
0
Papers:
22
Citations:
0

Organization

No organization information available