Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit diverse communities across the world. While previous efforts have focused on single-LLM, single-turn approaches, we propose to exploit the complementary strengths of multiple LLMs to promote cultural adaptability. We introduce a Multi-Agent Debate framework, where two LLM-based agents debate over a cultural scenario and collaboratively reach a final decision. We propose two variants: one where either LLM agents exclusively debate and another where they dynamically choose between self-reflection and debate during their turns. We evaluate these approaches on 7 open-weight LLMs (and 21 LLM combinations) using the NormAd-ETI benchmark for social etiquette norms in 75 countries. Experiments show that debate improves both overall accuracy and cultural group parity over single-LLM baselines. Notably, multi-agent debate enables relatively small LLMs (7-9B) to achieve accuracies comparable to that of a much larger model (27B parameters).

As people increasingly use AI systems in work and daily life, mechanisms that help them use AI responsibly are urgently needed, especially when they are not equipped to verify AI predictions themselves.We study a realistic Machine Translation (MT) scenario where monolingual users decide whether to share an MT output, first without and then with quality feedback.We compare four types of quality feedback: explicit feedback that directly give users an assessment of translation quality using (1) error highlights and (2) LLM explanations, and implicit feedback that helps users compare MT inputs and outputs through (3) backtranslation and ( 4) question-answer (QA) tables.We find that all feedback types, except error highlights, significantly improve both decision accuracy and appropriate reliance.Notably, implicit feedback, especially QA tables, yields significantly greater gains than explicit feedback in terms of decision accuracy, appropriate reliance, and user perceptions -receiving the highest ratings for helpfulness and trust, and the lowest for mental burden.

Yimin Xiao, Yongle Zhang, Dayeon Ki, Calvin Bao, Marianna J. Martindale, Charlotte Vaughn, Ge Gao, Marine Carpuat. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Dayeon Ki, Marine Carpuat. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.