# An Empirical Study of On-Device Translation for Real-Time Live-Stream Chat on Mobile Devices

arXiv: https://arxiv.org/abs/2601.02641 · HTML: https://mlsanity.com/paper/2601.02641/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean](https://mlsanity.com/paper/2403.06412/) (2024)
- [Scaling Low-Resource MT via Synthetic Data Generation with LLMs](https://mlsanity.com/paper/2505.14423/) (2025)
- [SlimLM: An Efficient Small Language Model for On-Device Document Assistance](https://mlsanity.com/paper/2411.09944/) (2024)
- [MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes](https://mlsanity.com/paper/2509.24945/) (2025)
- [Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation](https://mlsanity.com/paper/2403.16771/) (2024)
- [MQM-Chat: Multidimensional Quality Metrics for Chat Translation](https://mlsanity.com/paper/2408.16390/) (2024)

## Abstract (arXiv)

Despite its efficiency, there has been little research on the practical aspects required for real-world deployment of on-device AI models, such as the device's CPU utilization and thermal conditions. In this paper, through extensive experiments, we investigate two key issues that must be addressed to deploy on-device models in real-world services: (i) the selection of on-device models and the resource consumption of each model, and (ii) the capability and potential of on-device models for domain adaptation. To this end, we focus on a task of translating live-stream chat messages and manually construct LiveChatBench, a benchmark consisting of 1,000 Korean-English parallel sentence pairs. Experiments on five mobile devices provide a systematic empirical assessment of widely adopted on-device models, highlighting the importance of model selection and deployment constraints when adapting them to specialized tasks and serving a large and heterogeneous user base. We expect that our findings will offer practical insights into both the capabilities and limitations of on-device models for real-world AI service deployment.