AACL-IJCNLP 2026 tutorial tackles code-switching challenges for multilingual LLMs
thamar_solorio · x · 2026-11-09
The "Code-Switching for Multilingual LLMs" tutorial at AACL-IJCNLP 2026 (Hengqin, China) is led by researchers from NYU, KAIST, MBZUAI, Microsoft, and Capital One.
It covers sociolinguistic foundations, code-switching in human-AI interaction, datasets and benchmarks, synthetic data generation, multilingual LLM training and inference, mechanistic interpretability of unintended language switching, speech and multimodal code-switching, and societal impacts. Slides and a reading list are public, framing better multilingual LLMs as a key open challenge.
Related event: AACL-IJCNLP 2026 Hosts Tutorial on Code-Switching for Multilingual LLMs(2 posts)→
More from Research
- METR task-horizon debate: logistic rollover by 2027 or hyperbolic singularity? — teortaxesTex · 2026-11-09
- Composer's experiment: AI agents fed unquantized music sweep top 3 in blind creativity judging — Music-For-Robots · 2026-11-09
- Boltzina v1.1 uses NVIDIA BioNeMo to speed molecular docking up to 24.4x vs Boltz-2 — AllThingsApx · 2026-11-09
- Chinese blog post breaks down conic-lifting paper and its implications for schedule-free learning — bremen79 · 2026-11-09
- StatQuest releases long-form tutorial: Linear Discriminant Analysis concepts and Python code — StatQuest with Josh Starmer · 2026-11-09
- KAIST paper identifies 'Teacher Drift' in multilingual reasoning distillation and teaches only when it helps — Jaewon Cho · 2026-11-09