# Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages

arXiv: https://arxiv.org/abs/2503.23305 · HTML: https://mlsanity.com/paper/2503.23305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Confidence through Attention](https://mlsanity.com/paper/1710.03743/) (2017)
- [Modeling Confidence in Sequence-to-Sequence Models](https://mlsanity.com/paper/1910.01859/) (2019)
- [Improving Rare Word Translation With Dictionaries and Attention Masking](https://mlsanity.com/paper/2408.09075/) (2024)

## Abstract (arXiv)

We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing the user to intervene to correct mistranslations. However, confidence estimation in machine translation has traditionally focused on the target side. Whereas the conventional approach to source-side confidence estimation would have been to project target word probabilities to the source side via word alignments, we propose a direct, alignment-free approach that measures how sensitive the target word probabilities are to changes in the source embeddings. Experimental results show that our method outperforms traditional alignment-based methods at detection of mistranslations.