The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saji, Alan, Dabre, Raj, Kunchukuttan, Anoop, Puduppully, Ratish
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917256301117440
author Saji, Alan
Dabre, Raj
Kunchukuttan, Anoop
Puduppully, Ratish
author_facet Saji, Alan
Dabre, Raj
Kunchukuttan, Anoop
Puduppully, Ratish
contents Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks, but their multilingual reasoning abilities remain underexplored. When presented with non-English questions, LRMs often default to reasoning in English, raising concerns about interpretability and the handling of linguistic and cultural nuances. We systematically compare an LRM's reasoning in English versus the language of the question. Our evaluation spans two tasks: MGSM and GPQA Diamond. Beyond measuring answer accuracy, we also analyze cognitive attributes in the reasoning traces. We find that English reasoning traces exhibit a substantially higher presence of these cognitive behaviors, and that reasoning in English generally yields higher final-answer accuracy, with the performance gap increasing as tasks become more complex. However, this English-centric strategy is susceptible to a key failure mode - getting "Lost in Translation," where translation steps lead to errors that would have been avoided by reasoning in the language of the question.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20647
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI
Saji, Alan
Dabre, Raj
Kunchukuttan, Anoop
Puduppully, Ratish
Computation and Language
Artificial Intelligence
Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks, but their multilingual reasoning abilities remain underexplored. When presented with non-English questions, LRMs often default to reasoning in English, raising concerns about interpretability and the handling of linguistic and cultural nuances. We systematically compare an LRM's reasoning in English versus the language of the question. Our evaluation spans two tasks: MGSM and GPQA Diamond. Beyond measuring answer accuracy, we also analyze cognitive attributes in the reasoning traces. We find that English reasoning traces exhibit a substantially higher presence of these cognitive behaviors, and that reasoning in English generally yields higher final-answer accuracy, with the performance gap increasing as tasks become more complex. However, this English-centric strategy is susceptible to a key failure mode - getting "Lost in Translation," where translation steps lead to errors that would have been avoided by reasoning in the language of the question.
title The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.20647