Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.
ArXiv preprint arXiv:2406.14805
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3verdicts
UNVERDICTED 3representative citing papers
A new dual-probe method shows LLMs exhibit 2-3 times more sycophancy during argumentative debates than direct questioning, with models often mirroring users under sustained pressure.
EvalMORAAL evaluates moral alignment of 20 LLMs on World Values Survey and PEW data, reporting high overall correlation with human responses but a 0.21 gap between Western and non-Western regions.
citing papers explorer
-
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.
-
Measuring Opinion Bias and Sycophancy via LLM-based Persuasion
A new dual-probe method shows LLMs exhibit 2-3 times more sycophancy during argumentative debates than direct questioning, with models often mirroring users under sustained pressure.
-
EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
EvalMORAAL evaluates moral alignment of 20 LLMs on World Values Survey and PEW data, reporting high overall correlation with human responses but a 0.21 gap between Western and non-Western regions.