Fine-tuning LLMs on small pilot survey data balances structural, marginal, and individual fidelity better than prompting or rectification, but fidelity levels vary across subsamples in a COVID-19 misinformation case study.
arXiv preprint arXiv:2412.03162 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Bridging-inference knowledge graphs capture discourse-level semantic links that yield more coherent and stable LLM persona identification than lexical or stylistic baselines.
citing papers explorer
-
Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
Fine-tuning LLMs on small pilot survey data balances structural, marginal, and individual fidelity better than prompting or rectification, but fidelity levels vary across subsamples in a COVID-19 misinformation case study.
-
The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
Bridging-inference knowledge graphs capture discourse-level semantic links that yield more coherent and stable LLM persona identification than lexical or stylistic baselines.