Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results

• URL: http://arxiv.org/abs/2511.05162v1
• Date: Fri, 07 Nov 2025 11:30:10 GMT
• Title: Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results
• Authors: Jan-Thorsten Peter, David Vilar, Tobias Domhan, Dan Malkin, Markus Freitag,
• Abstract summary: We study the performance of different large language models (LLMs) across languages.<n>We find that there exists a non-negligible and consistent gap in the performance of the models across languages.<n>We propose a method for automatic quality assurance to address the first issue at scale, and give recommendations to address the second one.
• Score: 16.391752298134474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most current large language models (LLMs) support a wide variety of languages in addition to English, including high-resource languages (e.g. German, Chinese, French), as well as low-resource ones (e.g. Swahili, Telugu). In addition they have also shown impressive capabilities in different domains, like coding, science and math. In this short paper, taking math as an example domain, we study the performance of different LLMs across languages. Experimental results show that there exists a non-negligible and consistent gap in the performance of the models across languages. Interestingly, and somewhat against expectations, the gap exists for both high- and low-resource languages. We hope that these results influence further research into cross-lingual capability generalization for next generation LLMs. If it weren't for the fact that they are false! By analyzing one of the standard multilingual math benchmarks (MGSM), we determine that several translation errors are present in the data. Furthermore, the lack of standardized answer extraction from LLM outputs further influences the final results. We propose a method for automatic quality assurance to address the first issue at scale, and give recommendations to address the second one. Combining these two approaches we show that the aforementioned language gap mostly disappears, leading to completely different conclusions from our research. We additionally release the corrected dataset to the community.

Related papers

• Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains [6.357124887141297]
  Large Language Models (LLMs) have redefined Machine Translation (MT)<n>LLMs often exhibit uneven performance across language families and specialized domains.<n>We introduce Translation Tangles, a unified framework and dataset for evaluating the translation quality and fairness of open-source LLMs.
  arXiv  Detail & Related papers  (2025-10-09T07:28:30Z)
• Do LLMs exhibit the same commonsense capabilities across languages? [4.177608674029413]
  We introduce MULTICOM, a novel benchmark that extends the COCOTEROS dataset to four languages: English, Spanish, Dutch, and Valencian.<n>The task involves generating a commonsensical sentence that includes a given triplet of words.<n>Results consistently show superior performance in English, with significantly lower performance in less-resourced languages.
  arXiv  Detail & Related papers  (2025-09-08T07:47:00Z)
• Enhancing Code Generation for Low-Resource Languages: No Silver Bullet [55.39571645315926]
  Large Language Models (LLMs) rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages.<n>For low-resource languages, the limited availability of such data hampers the models' ability to generalize effectively.<n>We present an empirical study investigating the effectiveness of several approaches for boosting LLMs' performance on low-resource languages.
  arXiv  Detail & Related papers  (2025-01-31T12:23:28Z)
• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language.<n>Currently, instruction-tuned large language models (LLMs) excel at various English tasks.<n>Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages [25.402797722575805]
  Indic QA Benchmark is a dataset for context grounded question answering in 11 major Indian languages.<n> Evaluations revealed weak performance in low resource languages due to a strong English language bias in their training data.<n>We also investigated the Translate Test paradigm,where inputs are translated to English for processing and the results are translated back into the source language for output.
  arXiv  Detail & Related papers  (2024-07-18T13:57:16Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• 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)
• Evaluating and Mitigating Linguistic Discrimination in Large Language Models [7.634003893271555]
  Large language models (LLMs) can exhibit linguistic discrimination due to uneven distribution of training data across languages. We propose LDFighter, a similarity-based voting, to mitigate the linguistic discrimination in LLMs.
  arXiv  Detail & Related papers  (2024-04-29T09:22:54Z)
• Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages [48.40607157158246]
  Large Language Models (LLMs) perform better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate.<n>We propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations.<n>Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores.
  arXiv  Detail & Related papers  (2024-04-17T16:53:16Z)
• Could We Have Had Better Multilingual LLMs If English Was Not the Central Language? [4.655168524016426]
  Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on. Our study delves into Llama2's translation capabilities. Our experiments show that the 7B Llama2 model yields above 10 BLEU when translating into all languages it has seen.
  arXiv  Detail & Related papers  (2024-02-21T16:32:38Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• 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)
• X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models [103.75890012041366]
  Language models (LMs) have proven surprisingly successful at capturing factual knowledge. However, studies on LMs' factual representation ability have almost invariably been performed on English. We create a benchmark of cloze-style probes for 23 typologically diverse languages.
  arXiv  Detail & Related papers  (2020-10-13T05:29:56Z)

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.