mlsanityData to 14 Oct 2026

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

arXiv 2406.19482 ↗First posted 27 Jun 2024cs.CLcited by 17

Not on the map. Why?

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.

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

23 of 42 references.

References · 23

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  3. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  4. 2023Large Language Modelscited by 780
  5. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  6. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  7. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  8. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 206
  9. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
  10. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  11. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  12. 2023Faithfulness Tests for Natural Language Explanationscited by 107
11 more
  1. 2023The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluationcited by 95
  2. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  3. 2022Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Bettercited by 75
  4. 2023Leveraging GPT-4 for Automatic Translation Post-Editingcited by 56
  5. 2024Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuraciescited by 40
  6. 2023LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedbackcited by 39
  7. 2023Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationalescited by 37
  8. 2024Guiding Large Language Models to Post-Edit Machine Translation with Error Annotationscited by 22
  9. 2023Tailoring Self-Rationalizers with Multi-Reward Distillationcited by 21
  10. 2023The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metricscited by 15
  11. 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methodscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 4.

17 papers.

Sort:

By area:

  1. 2024MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluatorscited by 22
  2. 2025Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMscited by 7
  3. 2025Automatic Input Rewriting Improves Translation with Large Language Modelscited by 4
  4. 2024A Context-aware Framework for Translation-mediated Conversationscited by 2
  5. 2025Translation in the Wildcited by 2
  6. 2025TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Lawcited by 2
  7. 2026Strategies for Span Labeling with Large Language Modelscited by 2
  8. 2025Quality-Aware Decoding: Unifying Quality Estimation and Decodingcited by 1
  9. 2025Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Modelscited by 1
  10. 2025Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotationscited by 1
  11. 2025Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decodingcited by 0
  12. 2025LangMark: A Multilingual Dataset for Automatic Post-Editingcited by 0
5 more
  1. 2025FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writingcited by 0
  2. 2025When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Contentcited by 0
  3. 2026TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail Entitiescited by 0
  4. 2026Smarter edits? Post-editing with error highlights and translation suggestionscited by 0
  5. 2026North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)cited by 0