Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus

• URL: http://arxiv.org/abs/2609.06634v1
• Date: Sun, 06 Sep 2026 14:32:32 GMT
• Title: Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus
• Abstract summary: We report the system performances from the WMT2026 Test Suites shared task.<n>We received 31 MT systems' outputs covering English to Chinese (zh), Polish (pl), German (de), Arabic (ar)<n>We carried out automatic evaluations using BLEU, ChrF, BERT-score to select the Top3 systems per language pair, followed up with human evaluations on the selected systems.
• Score: 6.11187920238337
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLMs' performance on machine translation (MT) tasks is often dependent on the data availability in the specific domains and language pairs that they are trained upon. To examine if Multiword Expressions (MWEs) still set a bottleneck for LLMs regarding language understanding and translation, we report the system performances from the WMT2026 Test Suites shared task, for which we used the publicly available multilingual parallel corpus AlphaMWE as the test suites. We received 31 MT systems' outputs covering English to Chinese (zh), Polish (pl), German (de), Arabic (ar) including Modern Standard Arabic (MSA) and two dialectal ones (Egyptian and Tunisian Arabic). We carried out automatic evaluations using BLEU, ChrF, BERT-score to select the Top3 systems per language pair, followed up with human evaluations on the selected systems. Our findings show that: figurative/MWE phenomena remain challenging; automatic metrics sometimes disagree; human evaluation uncovers language-specific errors hidden by aggregate scores.

Related papers

• Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics [69.2321983942375]
  This work presents a comparative analysis of BLEU, an n-gram-based metric, and ChrF++, a character-based metric, for MT evaluation in ELRL settings.<n>We examine how each metric responds to translation artifacts, including hallucinations, repetition, source-text copying, and diacritic (textitmatra) variations across three ELRLs: Magahi, Bhojpuri, and Chhattisgarhi.<n>While recent work often relies solely on ChrF++, our findings show that BLEU, despite its lower absolute scores, provides complementary lexical-precision insights that improve interpretability.
  arXiv  Detail & Related papers  (2026-02-19T14:56:42Z)
• CEA-LIST at CheckThat! 2025: Evaluating LLMs as Detectors of Bias and Opinion in Text [3.9845507207125967]
  This paper presents a competitive approach to multilingual subjectivity detection using large language models (LLMs) with few-shot prompting.<n>We show that LLMs, when paired with carefully designed prompts, can match or outperform fine-tuned smaller language models (SLMs)<n>Our system achieved top rankings across multiple languages in the CheckThat! 2025 subjectivity detection task.
  arXiv  Detail & Related papers  (2025-07-10T08:35:05Z)
• mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks [14.0147704462457]
  We introduce mSTEB, a new benchmark to evaluate the performance of large language models (LLMs) on a wide range of tasks.<n>We evaluate the performance of leading LLMs such as Gemini 2.0 Flash and GPT-4o (Audio) and state-of-the-art open models such as Qwen 2 Audio and Gemma 3 27B.
  arXiv  Detail & Related papers  (2025-06-10T03:15:08Z)
• MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection [0.0]
  This paper describes our submission for SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes.<n>The task involves detecting hallucinated spans in text generated by instruction-tuned Large Language Models (LLMs) across multiple languages.<n>Our system ranked 1st in Arabic and Basque, 2nd in German, Swedish, and Finnish, and 3rd in Czech, Farsi, and French.
  arXiv  Detail & Related papers  (2025-05-27T08:26:17Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models [54.58989938395976]
  We introduce a decomposed prompting approach for sequence labeling tasks.<n>We test our method on the Universal Dependencies part-of-speech tagging dataset for 38 languages.
  arXiv  Detail & Related papers  (2024-02-28T15:15:39Z)
• Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic [1.0878040851638]
  We employ GPT-4 as a uniform evaluator for both English and Arabic queries to assess and compare the performance of the LLMs on various open-ended tasks. We find that fine-tuned base models using multilingual and multi-turn datasets could be competitive to models trained from scratch on multilingual data.
  arXiv  Detail & Related papers  (2023-10-23T11:40:04Z)
• The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants [80.4837840962273]
  We present Belebele, a dataset spanning 122 language variants. This dataset enables the evaluation of text models in high-, medium-, and low-resource languages.
  arXiv  Detail & Related papers  (2023-08-31T17:43:08Z)
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis [103.89753784762445]
  Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT) This paper systematically investigates the advantages and challenges of LLMs for MMT. We thoroughly evaluate eight popular LLMs, including ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2023-04-10T15:51:30Z)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning [98.60739735409243]
  Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks. We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
  arXiv  Detail & Related papers  (2023-04-03T18:46:01Z)
• Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models [57.80514758695275]
  Using large language models (LLMs) for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level. We propose a new prompting method called textbftextttError Analysis Prompting (EAPrompt) This technique emulates the commonly accepted human evaluation framework - Multidimensional Quality Metrics (MQM) and textitproduces explainable and reliable MT evaluations at both the system and segment level.
  arXiv  Detail & Related papers  (2023-03-24T05:05:03Z)
• LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation [94.33019040320507]
  Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features. Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases. We propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.
  arXiv  Detail & Related papers  (2022-10-19T12:21:39Z)
• AlphaMWE: Construction of Multilingual Parallel Corpora with MWE Annotations [5.8010446129208155]
  We present the construction of multilingual parallel corpora with annotation of multiword expressions (MWEs) The languages covered include English, Chinese, Polish, and German. We present a categorisation of the error types encountered by MT systems in performing MWE related translation.
  arXiv  Detail & Related papers  (2020-11-07T14:28:54Z)

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.