Test Set Quality in Multilingual LLM Evaluation

• URL: http://arxiv.org/abs/2508.02635v1
• Date: Mon, 04 Aug 2025 17:22:08 GMT
• Title: Test Set Quality in Multilingual LLM Evaluation
• Authors: Kranti Chalamalasetti, Gabriel Bernier-Colborne, Yvan Gauthier, Sowmya Vajjala,
• Abstract summary: We analyze recent multilingual evaluation sets in French and Telugu, identifying several errors in the process.<n>We argue that test sets should not be considered immutable and should be revisited, checked for correctness, and potentially versioned.
• Score: 2.3249139042158853
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Several multilingual benchmark datasets have been developed in a semi-automatic manner in the recent past to measure progress and understand the state-of-the-art in the multilingual capabilities of Large Language Models. However, there is not a lot of attention paid to the quality of the datasets themselves, despite the existence of previous work in identifying errors in even fully human-annotated test sets. In this paper, we manually analyze recent multilingual evaluation sets in two languages - French and Telugu, identifying several errors in the process. We compare the performance difference across several LLMs with the original and revised versions of the datasets and identify large differences (almost 10% in some cases) in both languages). Based on these results, we argue that test sets should not be considered immutable and should be revisited, checked for correctness, and potentially versioned. We end with some recommendations for both the dataset creators as well as consumers on addressing the dataset quality issues.

Related papers

• M-Prometheus: A Suite of Open Multilingual LLM Judges [64.22940792713713]
  We introduce M-Prometheus, a suite of open-weight LLM judges that can provide both direct assessment and pairwise comparison feedback on multilingual outputs.<n>M-Prometheus models outperform state-of-the-art open LLM judges on multilingual reward benchmarks spanning more than 20 languages, as well as on literary machine translation (MT) evaluation covering 4 language pairs.
  arXiv  Detail & Related papers  (2025-04-07T11:37:26Z)
• Evaluation of Multilingual Image Captioning: How far can we get with CLIP models? [3.902360015414256]
  This work presents several strategies, and extensive experiments, related to evaluating CLIPScore variants in multilingual settings.<n>Tests with machine-translated data show that multilingual CLIPScore models can maintain a high correlation with human judgements across different languages.
  arXiv  Detail & Related papers  (2025-02-10T16:00:00Z)
• P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs [84.24644520272835]
  We introduce P-MMEval, a large-scale benchmark covering effective fundamental and capability-specialized datasets.<n>P-MMEval delivers consistent language coverage across various datasets and provides parallel samples.<n>We conduct extensive experiments on representative multilingual model series to compare performances across models and tasks.
  arXiv  Detail & Related papers  (2024-11-14T01:29:36Z)
• Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models? [17.011882550422452]
  It is unknown whether the nature of the instruction data has an impact on the model output. It is questionable whether translated test sets can capture such nuances. We show that native or generation benchmarks reveal a notable difference between native and translated instruction data.
  arXiv  Detail & Related papers  (2024-06-18T17:43:47Z)
• On the Calibration of Multilingual Question Answering LLMs [57.296161186129545]
  We benchmark the calibration of several multilingual Large Language Models (MLLMs) on a variety of Question Answering tasks. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings. For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data.
  arXiv  Detail & Related papers  (2023-11-15T03:29:02Z)
• 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)
• Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages [15.373725507698591]
  We argue that this makes the existing practices in multilingual evaluation unreliable and does not provide a full picture of the performance of MMLMs across the linguistic landscape. We propose that the recent work done in Performance Prediction for NLP tasks can serve as a potential solution in fixing benchmarking in Multilingual NLP. We compare performance prediction with translating test data with a case study on four different multilingual datasets, and observe that these methods can provide reliable estimates of the performance that are often on-par with the translation based approaches.
  arXiv  Detail & Related papers  (2022-05-12T20:42:48Z)
• IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages [87.5457337866383]
  We introduce the Image-Grounded Language Understanding Evaluation benchmark. IGLUE brings together visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. We find that translate-test transfer is superior to zero-shot transfer and that few-shot learning is hard to harness for many tasks.
  arXiv  Detail & Related papers  (2022-01-27T18:53:22Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)
• X-FACT: A New Benchmark Dataset for Multilingual Fact Checking [21.2633064526968]
  We introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers.
  arXiv  Detail & Related papers  (2021-06-17T05:09:54Z)
• XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization [98.61159823343036]
  We present the Word-in-Context dataset (WiC) for assessing the ability to correctly model distinct meanings of a word. We put forward a large multilingual benchmark, XL-WiC, featuring gold standards in 12 new languages. Experimental results show that even when no tagged instances are available for a target language, models trained solely on the English data can attain competitive performance.
  arXiv  Detail & Related papers  (2020-10-13T15:32:00Z)

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.