# FACET at WMT 2026 Automated Translation Quality Evaluation Task

arXiv: https://arxiv.org/abs/2610.00096 · HTML: https://mlsanity.com/paper/2610.00096/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [TransQuest: Translation Quality Estimation with Cross-lingual Transformers](https://mlsanity.com/paper/2011.01536/) (2020)
- [MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators](https://mlsanity.com/paper/2409.14335/) (2024)
- [COMET-QE and Active Learning for Low-Resource Machine Translation](https://mlsanity.com/paper/2210.15696/) (2022)
- [Do LLMs Truly Benefit from Longer Context in Automatic Post-Editing?](https://mlsanity.com/paper/2601.19410/) (2026)

## Abstract (arXiv)

Different error types in machine translation require different evidence. Whether meaning is preserved can be judged only against the source, while whether the target is well-formed, or whether it names one entity consistently, can be judged from the target alone. We present FACET, our reference-free submission to the WMT26 Automated Translation Quality Evaluation Task, which decomposes evaluation into Fluency, Accuracy, and Consistency passes and gives each pass only the context its error type requires. A single fixed model is prompted three times, and the merged error spans yield the three task outputs, error spans, quality scores, and error-free labels, with no trained components. We also submit FACET-C, which omits the Consistency pass. Without gold labels, we characterize the predictions of FACET. Its system rankings place post-edited human translation first, and the Consistency pass changes about a tenth of segment scores while leaving the ranking nearly unchanged.