HACHIMI generates a 1M corpus of controllable, theory-aligned student personas via orchestrated agents, achieving high schema validity and partial alignment with real survey responses on math and curiosity measures.
InProceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 52–64
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents
HACHIMI generates a 1M corpus of controllable, theory-aligned student personas via orchestrated agents, achieving high schema validity and partial alignment with real survey responses on math and curiosity measures.