# OLA: Output Language Alignment in Code-Switched LLM Interactions

arXiv: https://arxiv.org/abs/2601.03589 · HTML: https://mlsanity.com/paper/2601.03589/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 23 of 23)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [LLaMA Beyond English: An Empirical Study on Language Capability Transfer](https://mlsanity.com/paper/2401.01055/) (2024)
- [Do Multilingual Language Models Think Better in English?](https://mlsanity.com/paper/2308.01223/) (2023)
- [Do Multilingual LLMs Think In English?](https://mlsanity.com/paper/2502.15603/) (2025)
- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://mlsanity.com/paper/2305.14235/) (2023)
- [The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges](https://mlsanity.com/paper/2212.09660/) (2022)
- [Language Tags Matter for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2106.07930/) (2021)
- [Code-Switching Curriculum Learning for Multilingual Transfer in LLMs](https://mlsanity.com/paper/2411.02460/) (2024)
- [Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes](https://mlsanity.com/paper/2505.14815/) (2025)
- [Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models](https://mlsanity.com/paper/2507.12428/) (2025)
- [SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset](https://mlsanity.com/paper/2506.00087/) (2025)
- [The Impact of Language Mixing on Bilingual LLM Reasoning](https://mlsanity.com/paper/2507.15849/) (2025)
- [The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure](https://mlsanity.com/paper/2506.22724/) (2025)
- [Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer](https://mlsanity.com/paper/2402.14279/) (2024)
- [Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching](https://mlsanity.com/paper/2410.18436/) (2024)

## Built on by (most cited first, 3 of 3)

- [Code-Switching Reveals Language Anchoring in Multilingual LLMs](https://mlsanity.com/paper/2606.19668/) (2026)
- [Steering the Language Axis: From Linear Decodability to Causal Control](https://mlsanity.com/paper/2608.12334/) (2026)
- [CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing](https://mlsanity.com/paper/2610.20272/) (2026)

## Abstract (arXiv)

Code-switching, alternating between languages within a conversation, is natural for multilingual users, yet poses fundamental challenges for large language models (LLMs). When a user code-switches in their prompt to an LLM, they typically do not specify the expected language of the LLM response, and thus LLMs must infer the output language from contextual and pragmatic cues. We find that current LLMs systematically fail to align with this expectation, responding in undesired languages even when cues are clear to humans. We introduce OLA, a benchmark to evaluate LLMs' Output Language Alignment in code-switched interactions. OLA focuses on Korean--English code-switching and spans simple intra-sentential mixing to instruction-content mismatches. Even frontier models frequently misinterpret implicit language expectation, exhibiting a bias toward non-English responses. We further show this bias generalizes beyond Korean to Chinese and Indonesian pairs. Models also show instability through mid-response switching and language intrusions. Chain-of-Thought prompting fails to resolve these errors, indicating weak pragmatic reasoning about output language. However, Code-Switching Aware DPO with minimal data (about 1K examples) substantially reduces misalignment, suggesting these failures stem from insufficient alignment rather than fundamental limitations. Our results highlight the need to align multilingual LLMs with users' implicit expectations in real-world code-switched interactions.