Code-Switching

Follow this topic Ask about this topic

Code-switching research examines how speakers alternate languages within conversations and how mixed-language forms relate to borrowing, identity, emotion, and context. Computational work uses annotated text and speech corpora, token-level language identification, multilingual encoders, and adapted automatic speech recognition, with evaluations spanning sentiment, named entities, reasoning, and safety. Recent approaches also steer language representations or train models progressively to reason and write across languages, while sociolinguistic analyses measure which language is used and when switches occur. A persistent challenge is that results depend on how annotations distinguish borrowings from switches, and models still struggle with morphologically integrated words and context-appropriate switching.

Latest papers

22 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Benchmarking Large Language Models for Detecting Satirical Code-Mixed Sentences
Oct 21, 2026Răzvan-Alexandru Smădu, Ioana Buhnila, Daniela Tanase +3Code-Switching Text Classification
National University of Science and Technology POLITEHNICA Bucharest, Bucharest, Romania · Academy of Romanian Scientists, Bucharest, Romania · Center for Data Science in Humanities, Chosun University, South Korea +3
From Unverifiable Domain Text to Cross-Lingual RLVR via Code-Switched Task Synthesis
Oct 18, 2026Cheonbok Park, Jihwan Kim, Shinyoung Joo +4Cross-Lingual Transfer Code-Switching
NAVER Cloud · KAIST AI
CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing
Oct 14, 2026Zewen Jiang, Yahan Li, Chenlu Guo +3Code-Switching Multilingual Language Model Evaluation
School of Artificial Intelligence, Jilin University, China · College of Software, Jilin University, China · Xingchen AGI Lab, China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd., China +4
Domain-specific Pretraining Profile and Transformer Performance: Evidence from Modeling Digital Pragmatics in Arabic-English Code-switching
Sep 13, 2026Fahad Al Hussen, King Saud University, Riyadh +5Arabic NLP Pragmatic Reasoning in Language Models
King Saud University, Riyadh, Saudi Arabia · Ibb University, Ibb, Yemen
TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity Recognition
Sep 7, 2026Ilayda Dogan, Phuong-Anh Nguyen-Le, Julia MendelsohnCode-Switching Language Identification
Computer Science University of Maryland
Latent Mechanisms of Language Control in Multilingual Language Models
Aug 31, 2026Ryo Mitsuhashi, Sabri Boughorbel, Majd HawaslyMultilingual Language Models Multilingual Language Model Evaluation
Princeton University New Jersey, USA · Prince Sattam bin Abdulaziz University Riyadh, Saudi Arabia · QCRI, Hamad Bin Khalifa University, Doha, Qatar
Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish
Aug 25, 2026Tanveer SinghLLM Hallucination Detection Language Model Probing
Plaksha University
PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing
Aug 10, 2026Ghazal Kalhor, Zahra Jafari, Amirarsalan Shahbazi +1Social Media Analysis Code-Switching
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran · Tehran Institute for Advanced Studies, Khatam University, Tehran, Iran
Loanword or Switch? The Annotation Boundary, Not the Model, Drives Kazakh-Russian Code-Switching Identification
Aug 1, 2026Bogdan SavelyevCode-Switching Language Identification
Independent Researcher Kazakhstan
Evaluation of forced alignment of code-mixed speech: the case of Hindi-English
Jul 28, 2026Ayushi Pandey, Pamir Gogoi, Kevin TangCode-Switching Speech Recognition Code-Switching
Karya, India · Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf, Germany · Department of Linguistics, University of Florida, United States of America
A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings
Jul 28, 2026Debasmita Bhattacharya, Siying Ding, Alayna Nguyen +1Code-Switching Interpretable ML
Department of Computer Science, Columbia University · Instagram
Efficient Multilingual Reasoning Transfer via Progressive Code-Switching
Jul 1, 2026Zhijun Wang, Junxiao Liu, Hao Zhou +3Code-Switching Cross-Lingual Reasoning in Language Models
National Key Laboratory for Novel Software Technology, Nanjing University, China · Tongyi Lab, Alibaba Group
Adding Robust Code-Switching Capabilities to High Performance Multilingual ASR
Jun 20, 2026Enes Yavuz Ugan, Alexander WaibelCode-Switching Speech Recognition Code-Switching
Interactive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany · InterACT, Carnegie Mellon University (CMU), USA
Code-Switching Reveals Language Anchoring in Multilingual LLMs
Jun 18, 2026Jeonghyun Park, Seunghyun Yoon, Yonghyun Jun +1Multilingual Language Models Code-Switching
Chung-Ang University, Seoul, Korea · Adobe Research, USA
CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech
Jun 9, 2026Brian Yan, Qingzheng Wang, Matthew Wiesner +9Code-Switching Speech Processing
Carnegie Mellon University · Johns Hopkins University · University of Texas at Austin +4
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech
Jun 4, 2026Virginia Ceccatelli, Yejin Jeon, David Ifeoluwa AdelaniAudio-Language Model Evaluation Language Model Safety Evaluation
Mila - Quebec AI Institute · McGill University, Canada · Canada CIFAR AI Chair
Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
May 28, 2026Shunta Asano, Jeonghun Baek, Toshihiko YamasakiMultilingual Language Models Code-Switching
The University of Tokyo
Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch
Apr 16, 2026Eleanor M. Lin, David JurgensMultilingual Language Models Code-Switching
University of Michigan
EnTaCs: Analyzing the Relationship Between Sentiment and Language Choice in English-Tamil Code-Switching
Mar 27, 2026Paul BontempoCode-Switching
University of Colorado, Boulder Depts. of Computer Science and Linguistics
Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders
Mar 20, 2026Debajyoti Mazumder, Divyansh Pathak, Prashant Kodali +1Multilingual Language Models Code-Switching
Indian Institute of Science Education and Research, Bhopal, India · Microsoft Corporation
LuxBorrow: From Pompier to Pompjee, Tracing Borrowing in Luxembourgish
Mar 11, 2026Nina Hosseini-Kivanani, Fred PhilippyCode-Switching
University of Luxembourg, Luxembourg · Radio Télévision Luxembourg (RTL), Luxembourg · SnT, University of Luxembourg, Luxembourg
Language steering in latent space to mitigate unintended code-switching
Oct 11, 2025Andrey Goncharov, Nikolai Kondusov, Alexey ZaytsevLanguage Model Steering Multilingual Language Models

Oct 21, 2026J/K move · Enter open · S save

Benchmarking Large Language Models for Detecting Satirical Code-Mixed Sentences

Răzvan-Alexandru Smădu, Ioana Buhnila, Daniela Tanase, Dumitru-Clementin Cercel+2

National University of Science and Technology POLITEHNICA Bucharest, Bucharest, Romania · Academy of Romanian Scientists, Bucharest, Romania · Center for Data Science in Humanities, Chosun University, South Korea+3

Code-Switching Text Classification Multilingual Language Model Evaluation Synthetic Data Generation for Language Models Low-Resource Language Processing

Open paper AskPDF arXiv

Code-switching is a natural linguistic phenomenon, yet its impact on high-level reasoning tasks remains largely unexplored in under-resourced languages like Romanian. Natural language processing tasks, such as satire detection, rely heavily on nuanced cultural and syntactic cues that large language models struggle to capture. In this paper, we investigate four methods (i.e., random replacement, phrase translation, dependency parsing, and large language models) for generating synthetic code-mixed Romanian sentences with English, German, French, and Italian. We start with an existing dataset for satire detection, compiled from Romanian news articles and annotated at the sentence level by humans, and augment it with over 600k samples, namely CS-SeLeRoSa. We provide an in-depth analysis of the dataset generation process. Then, we evaluate several multilingual large language models across zero-shot, chain-of-thought, and fine-tuning regimes on both the synthetic corpus and a human-adjudicated gold benchmark, namely CS-SeLeRoSa-Gold. While older open models suffer substantial degradation (dropping to 37%-55% macro-F1), newer models like Gemma 4 31B achieve 68.1% zero-shot, rivaling frontier models like GPT-5 mini (69.5%). Furthermore, fine-tuning significantly reduces formatting errors and improves the results, increasing Gemma 4 31B to 77.5% on CS-SeLeRoSa and 72.6% on the gold standard, outperforming frontier zero-shot baselines.