Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation

• URL: http://arxiv.org/abs/2605.24904v1
• Date: Sun, 24 May 2026 07:06:34 GMT
• Title: Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
• Abstract summary: Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs)<n>We address two practical gaps: how well automatic MQM-style error spans from LLM judges and a span-aware QE baseline.<n>We find that span agreement is non-trivial on naturally occurring benchmark translations, and that target-side translation errors are consistently associated with measurable, percentage-point drops in translated accuracy.
• Score: 8.48956061615262
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliability and comparability of multilingual evaluation. We address two practical gaps: (i) how well automatic MQM-style error spans from LLM judges and a span-aware QE baseline (xCOMET-XXL) match expert human span annotations on benchmark translations, and (ii) how strongly translation errors (as opposed to source-side issues in the English original) explain accuracy drops on translated benchmarks. We find that span agreement is non-trivial on naturally occurring benchmark translations, and that target-side translation errors are consistently associated with measurable, percentage-point drops in translated accuracy even after controlling for English correctness and source-side anomalies.

Related papers

• SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection [0.0]
  We introduce Systematic Wikidata-based Object-Relation Distortion (SWORD), a benchmark that evaluates whether models consistently reject factual errors across languages.<n>SWORD generates syntactically well-formed but factually incorrect statements in eight widely spoken languages through controlled perturbations of Wikidata triples.<n>Our evaluation surfaces two critical insights that remain entirely obscured by conventional benchmarks.
  arXiv  Detail & Related papers  (2026-09-08T18:39:01Z)
• XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics [64.77152900881724]
  We propose XQ-MEval, a semi-automatically built dataset covering nine translation directions.<n>We inject MQM-defined errors into gold translations automatically, filter them by native speakers for reliability, and merge errors to generate pseudo translations with controllable quality.<n>Using XQ-MEval, our experiments on nine representative metrics reveal the inconsistency between averaging and human judgment.
  arXiv  Detail & Related papers  (2026-04-16T12:27:10Z)
• Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation [57.11989521509119]
  We propose a novel agentic translation evaluation framework, centered by a reflective Core Agent that invokes specialized sub-agents.<n> Experimental results indicate the efficacy of RATE, achieving an improvement of at least 3.2 meta score compared with current metrics.
  arXiv  Detail & Related papers  (2026-01-12T09:03:42Z)
• Quality-Aware Translation Tagging in Multilingual RAG system [0.3876459156082311]
  We propose Quality-Aware Translation Tagging in mRAG (QTT-RAG)<n>QTT-RAG explicitly evaluates translation quality along three dimensions-semantic equivalence, grammatical accuracy, and naturalness&fluency.<n>This approach allows for effective usage of cross-lingual documents in low-resource settings with limited native language documents.
  arXiv  Detail & Related papers  (2025-10-27T07:11:01Z)
• LLM-based Translation Inference with Iterative Bilingual Understanding [52.46978502902928]
  We propose a novel Iterative Bilingual Understanding Translation method based on the cross-lingual capabilities of large language models (LLMs)<n>The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately.<n>The proposed IBUT outperforms several strong comparison methods.
  arXiv  Detail & Related papers  (2024-10-16T13:21:46Z)
• MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators [53.91199933655421]
  Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment.<n>We introduce a universal and training-free framework, $textbfMQM-APE, based on the idea of filtering out non-impactful errors.<n>Experiments show that our approach consistently improves both the reliability and quality of error spans against GEMBA-MQM.
  arXiv  Detail & Related papers  (2024-09-22T06:43:40Z)
• Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning [26.49647954587193]
  In this work, we find that translation inconsistencies do exist and they disproportionally impact low-resource languages in XNLI. To identify such inconsistencies, we propose measuring the gap in performance between zero-shot evaluations on the human-translated and machine-translated target text. We also corroborate that translation errors exist for two target languages, namely Hindi and Urdu, by doing a manual reannotation of human-translated test instances.
  arXiv  Detail & Related papers  (2024-02-03T08:22:51Z)
• Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets [92.38654521870444]
  We introduce ACES, a contrastive challenge set spanning 146 language pairs. This dataset aims to discover whether metrics can identify 68 translation accuracy errors. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks.
  arXiv  Detail & Related papers  (2024-01-29T17:17:42Z)
• xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection [21.116517555282314]
  xCOMET is an open-source learned metric designed to bridge the gap between machine translation evaluation approaches. It integrates both sentence-level evaluation and error span detection capabilities, exhibiting state-of-the-art performance across all types of evaluation. We also provide a robustness analysis with stress tests, and show that xCOMET is largely capable of identifying localized critical errors and hallucinations.
  arXiv  Detail & Related papers  (2023-10-16T15:03:14Z)
• On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation [55.02832094101173]
  Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual similarity. This paper concerns ourselves with reference-free machine translation (MT) evaluation where we directly compare source texts to (sometimes low-quality) system translations. We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER. We find that they perform poorly as semantic encoders for reference-free MT evaluation and identify their two key limitations.
  arXiv  Detail & Related papers  (2020-05-03T22:10:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.