# MTUncertainty: Assessing the Need for Post-editing of Machine Translation Outputs by Fine-tuning OpenAI LLMs

arXiv: https://arxiv.org/abs/2308.00158 · HTML: https://mlsanity.com/paper/2308.00158/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [HOPE: A Task-Oriented and Human-Centric Evaluation Framework Using Professional Post-Editing Towards More Effective MT Evaluation](https://mlsanity.com/paper/2112.13833/) (2021)
- [Measuring Uncertainty in Translation Quality Evaluation (TQE)](https://mlsanity.com/paper/2111.07699/) (2021)
- [Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task](https://mlsanity.com/paper/2210.10049/) (2022)

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

- [The Multi-Range Theory of Translation Quality Measurement: MQM scoring models and Statistical Quality Control](https://mlsanity.com/paper/2405.16969/) (2024)

## Abstract (arXiv)

Translation Quality Evaluation (TQE) is an essential step of the modern translation production process. TQE is critical in assessing both machine translation (MT) and human translation (HT) quality without reference translations. The ability to evaluate or even simply estimate the quality of translation automatically may open significant efficiency gains through process optimisation. This work examines whether the state-of-the-art large language models (LLMs) can be used for this purpose. We take OpenAI models as the best state-of-the-art technology and approach TQE as a binary classification task. On eight language pairs including English to Italian, German, French, Japanese, Dutch, Portuguese, Turkish, and Chinese, our experimental results show that fine-tuned gpt3.5 can demonstrate good performance on translation quality prediction tasks, i.e. whether the translation needs to be edited. Another finding is that simply increasing the sizes of LLMs does not lead to apparent better performances on this task by comparing the performance of three different versions of OpenAI models: curie, davinci, and gpt3.5 with 13B, 175B, and 175B parameters, respectively.