# When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering

Source: [When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering](<https://www.sota2.com/research/paper/68fa78e81e209131cea7b231>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-12T05:01:41.943Z

Authors: Eojin Kang, Juae Kim

Published: 2025-05-30T09:47:25.000Z

## Abstract

Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English prompting and evaluation, assuming that English-based reasoning is universally beneficial. In this work, we challenge that assumption by exploring factual knowledge transfer from non-English to English through the lens of Language and Thought Theory. We introduce Language-to-Thought (L2T) prompting, which aligns the model's internal ''thinking'' language with the source of knowledge. Across three languages and four models, L2T consistently outperforms English-based reasoning, reversing the expected advantage of English prompts. Our code is available at https://github.com/GeomeunByeol/Language2Thought.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.24409>)

[PDF](<https://arxiv.org/pdf/2505.24409.pdf>)