# xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

arXiv: https://arxiv.org/abs/2406.19482 · HTML: https://mlsanity.com/paper/2406.19482/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation](https://mlsanity.com/paper/2308.07286/) (2023)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better](https://mlsanity.com/paper/2212.08597/) (2022)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies](https://mlsanity.com/paper/2401.06760/) (2024)
- [LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback](https://mlsanity.com/paper/2311.09336/) (2023)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations](https://mlsanity.com/paper/2404.07851/) (2024)
- [Tailoring Self-Rationalizers with Multi-Reward Distillation](https://mlsanity.com/paper/2311.02805/) (2023)
- [The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics](https://mlsanity.com/paper/2305.11806/) (2023)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)

## Built on by (most cited first, 17 of 17)

- [MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators](https://mlsanity.com/paper/2409.14335/) (2024)
- [Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs](https://mlsanity.com/paper/2512.16378/) (2025)
- [Automatic Input Rewriting Improves Translation with Large Language Models](https://mlsanity.com/paper/2502.16682/) (2025)
- [A Context-aware Framework for Translation-mediated Conversations](https://mlsanity.com/paper/2412.04205/) (2024)
- [Translation in the Wild](https://mlsanity.com/paper/2505.23548/) (2025)
- [TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law](https://mlsanity.com/paper/2507.00875/) (2025)
- [Strategies for Span Labeling with Large Language Models](https://mlsanity.com/paper/2601.16946/) (2026)
- [Quality-Aware Decoding: Unifying Quality Estimation and Decoding](https://mlsanity.com/paper/2502.08561/) (2025)
- [Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Models](https://mlsanity.com/paper/2505.01761/) (2025)
- [Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations](https://mlsanity.com/paper/2512.18906/) (2025)
- [Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding](https://mlsanity.com/paper/2510.06866/) (2025)
- [LangMark: A Multilingual Dataset for Automatic Post-Editing](https://mlsanity.com/paper/2511.17153/) (2025)
- [FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writing](https://mlsanity.com/paper/2511.22883/) (2025)
- [When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content](https://mlsanity.com/paper/2512.17738/) (2025)
- [TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail Entities](https://mlsanity.com/paper/2603.27768/) (2026)
- [Smarter edits? Post-editing with error highlights and translation suggestions](https://mlsanity.com/paper/2605.21135/) (2026)
- [North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)](https://mlsanity.com/paper/2609.13916/) (2026)

## Abstract (arXiv)

While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the translation quality and user experience. This paper introduces xTower, an open large language model (LLM) built on top of TowerBase designed to provide free-text explanations for translation errors in order to guide the generation of a corrected translation. The quality of the generated explanations by xTower are assessed via both intrinsic and extrinsic evaluation. We ask expert translators to evaluate the quality of the explanations across two dimensions: relatedness towards the error span being explained and helpfulness in error understanding and improving translation quality. Extrinsically, we test xTower across various experimental setups in generating translation corrections, demonstrating significant improvements in translation quality. Our findings highlight xTower's potential towards not only producing plausible and helpful explanations of automatic translations, but also leveraging them to suggest corrected translations.