# Cross-Lingual Exploration for Parametric Knowledge

Authors: Elisha Diskind, I. Trainin, Uri Shaham, Leshem Choshen, Idan Szpektor, Omri Abend
Venue: preprint (2026)

## Abstract
Parametric 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 cross-lingual prompting strategies. 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 observe corresponding improvements in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work establishes multilingual prompt exploration as a highly effective inference-time strategy for unlocking latent parametric knowledge.

## Links
- arXiv: https://arxiv.org/abs/2606.24579
- PDF: https://arxiv.org/pdf/2606.24579
- HTML: https://ar5iv.labs.arxiv.org/html/2606.24579
- Hugging Face: https://huggingface.co/papers/2606.24579
- alphaXiv: https://www.alphaxiv.org/abs/2606.24579
- Semantic Scholar: https://www.semanticscholar.org/paper/289628562