.png){kind=icon}
Return
Coordinated LLM multi-agent systems for collaborative question-answer generation
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2025.114627.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose CIR3, a novel framework for comprehensive and faithful QA generation. • The efficient information flow of CIR3 enables in-depth document analysis. • We employ transactive reasoning for deeper understanding in CIR3. • Our approach’s multi-perspective assessment ensures balanced views. • CIR3’s balanced collective convergence yields robust results. • CIR3 improves QA comprehensiveness (+23) and faithfulness (+17).
Keywords:
Question-answer generation
Data augmentation
Large language models
Multi-agent coordination
Multi-perspective analysis
Domain-specific
Cross-model agreement
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
K
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSave
View more