# The Impact of Language Mixing on Bilingual LLM Reasoning

arXiv: https://arxiv.org/abs/2507.15849 · HTML: https://mlsanity.com/paper/2507.15849/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 18 of 18)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs](https://mlsanity.com/paper/2210.12283/) (2022)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [Thinking with Generated Images](https://mlsanity.com/paper/2505.22525/) (2025)
- [Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?](https://mlsanity.com/paper/2408.10811/) (2024)
- [The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling](https://mlsanity.com/paper/2410.09223/) (2024)
- [Tina: Tiny Reasoning Models via LoRA](https://mlsanity.com/paper/2504.15777/) (2025)
- [Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training](https://mlsanity.com/paper/2504.01801/) (2025)
- [Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training](https://mlsanity.com/paper/2504.20484/) (2025)

## Built on by (most cited first, 12 of 12)

- [Language of Thought Shapes Output Diversity in Large Language Models](https://mlsanity.com/paper/2601.11227/) (2026)
- [Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs](https://mlsanity.com/paper/2510.05678/) (2025)
- [OLA: Output Language Alignment in Code-Switched LLM Interactions](https://mlsanity.com/paper/2601.03589/) (2026)
- [Tandem Training for Language Models](https://mlsanity.com/paper/2510.13551/) (2025)
- [Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch](https://mlsanity.com/paper/2604.15490/) (2026)
- [Reading Between the Dots: Decoding Hidden Computation across Filler Tokens](https://mlsanity.com/paper/2607.03502/) (2026)
- [Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation](https://mlsanity.com/paper/2510.17555/) (2025)
- [Learning to Route Languages for Multilingual Policy Optimization](https://mlsanity.com/paper/2605.25360/) (2026)
- [HiMed: Incentivizing Hindi Reasoning in Medical LLMs](https://mlsanity.com/paper/2605.24635/) (2026)
- [Tandem Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2606.28166/) (2026)
- [What Does Post-Training Change in Multilingual Reasoning?](https://mlsanity.com/paper/2609.37104/) (2026)
- [Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol](https://mlsanity.com/paper/2610.04295/) (2026)

## Abstract (arXiv)

Proficient multilingual speakers often intentionally switch languages in the middle of a conversation. Similarly, recent reasoning-focused bilingual large language models (LLMs) with strong capabilities in both languages exhibit language mixing-alternating languages within their chain of thought. Discouraging this behavior in DeepSeek-R1 was found to degrade accuracy, suggesting that language mixing may benefit reasoning. In this work, we study language switching in Chinese-English bilingual reasoning models. We identify reinforcement learning with verifiable rewards (RLVR) as the critical training stage that leads to language mixing. We show that language mixing can enhance reasoning: enforcing monolingual decoding reduces accuracy by 5.6 percentage points on MATH500. Additionally, a lightweight probe can be trained to predict whether a potential language switch would benefit or harm reasoning, and when used to guide decoding, increases accuracy by 2.92 percentage points. Our findings suggest that language mixing is not merely a byproduct of multilingual training, but is a strategic reasoning behavior.