Do Language Models Reason Across Languages?

arXiv:2601.06644 · cs.CL, cs.AI · Submitted 2026-01-10 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-01-10

Updated: 2026-08-31

Code: https://github.com/MicrosoftTranslator/NTREX

Terminology

• Accuracy — 10× in this paper · explained in 1 episode
• Multi-hop Reasoning — 6× in this paper · explained in 3 episodes
• F1 Score — 3× in this paper · explained in 3 episodes
• Failure Modes — 3× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Low-Resource Languages — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
• A Survey of Multilingual Reasoning in Language Models
• How Do LLMs Perform Two-Hop Reasoning in Context?
• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
• Gemma 3 Technical Report
• Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
• Premise Order Matters in Reasoning with Large Language Models
• Understanding Neural Networks through Representation Erasure
• Logical Reasoning in Large Language Models: A Survey
• Multilingual Prompting for Improving LLM Generation Diversity
• Chain-of-Thought Reasoning Without Prompting
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering