# How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation

arXiv: https://arxiv.org/abs/2511.09748 · HTML: https://mlsanity.com/paper/2511.09748/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [mmBERT: A Modern Multilingual Encoder with Annealed Language Learning](https://mlsanity.com/paper/2509.06888/) (2025)
- [SynCED-EnDe 2025: A Synthetic and Curated English - German Dataset for Critical Error Detection in Machine Translation](https://mlsanity.com/paper/2510.05144/) (2025)

## Built on by (most cited first, 1 of 1)

- [Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs](https://mlsanity.com/paper/2609.07664/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) excel at evaluating machine translation (MT), but their scale and cost hinder deployment on edge devices and in privacy-sensitive workflows. We ask: how small can you get while still detecting meaning-altering translation errors? Focusing on English->German Critical Error Detection (CED), we benchmark sub-2B models (LFM2-350M, Qwen-3-0.6B/1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B) across WMT21, WMT22, and SynCED-EnDe-2025. Our framework standardizes prompts, applies lightweight logit-bias calibration and majority voting, and reports both semantic quality (MCC, F1-ERR/F1-NOT) and compute metrics (VRAM, latency, throughput). Results reveal a clear sweet spot around one billion parameters: Gemma-3-1B provides the best quality-efficiency trade-off, reaching MCC=0.77 with F1-ERR=0.98 on SynCED-EnDe-2025 after merged-weights fine-tuning, while maintaining 400 ms single-sample latency on a MacBook Pro M4 Pro (24 GB). At larger scale, Qwen-3-1.7B attains the highest absolute MCC (+0.11 over Gemma) but with higher compute cost. In contrast, ultra-small models (0.6B) remain usable with few-shot calibration yet under-detect entity and number errors. Overall, compact, instruction-tuned LLMs augmented with lightweight calibration and small-sample supervision can deliver trustworthy, on-device CED for MT, enabling private, low-cost error screening in real-world translation pipelines. All datasets, prompts, and scripts are publicly available at our GitHub repository.