Fine-tuning a lightweight LLM with attribute sequences ordered by a Bayesian network produces synthetic populations with about 95% feasibility while preserving recall comparable to deep generative models.
In contrast, we use a dataset constructed by merging the South Korean HTS conducted in 2010, 2016, and 2021, resulting in over one million records
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Large Language Model for Feasible and Diverse Population Synthesis
Fine-tuning a lightweight LLM with attribute sequences ordered by a Bayesian network produces synthetic populations with about 95% feasibility while preserving recall comparable to deep generative models.