Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Cross-Lingual Exploration for Parametric Knowledge

AbstractParametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring the prompted questions across languages. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we report similar performance improvement in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work demonstrates the potential of multilingual exploration to improve parametric knowledge recall.

More from EMNLP 2026

All EMNLP 2026 papers →