DISCA converts within-country disagreement among World Values Survey personas into a bounded logit correction that reduces cultural misalignment by 10-24% on MultiTP for models 3.8B and larger across 20 countries, without any weight updates.
PsyArXiv preprint , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
Teachers' views on AI benefits and risks vary widely across 55 countries, but LLMs compress these differences, overestimate both sides, and show little improvement from country prompting or better reasoning.
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.
citing papers explorer
-
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
DISCA converts within-country disagreement among World Values Survey personas into a bounded logit correction that reduces cultural misalignment by 10-24% on MultiTP for models 3.8B and larger across 20 countries, without any weight updates.
-
Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability
Teachers' views on AI benefits and risks vary widely across 55 countries, but LLMs compress these differences, overestimate both sides, and show little improvement from country prompting or better reasoning.
-
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.