Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contamination

• URL: http://arxiv.org/abs/2409.12746v2
• Date: Tue, 14 Jan 2025 16:41:28 GMT
• Title: Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contamination
• Authors: Eva Sánchez Salido, Roser Morante, Julio Gonzalo, Guillermo Marco, Jorge Carrillo-de-Albornoz, Laura Plaza, Enrique Amigó, Andrés Fernández, Alejandro Benito-Santos, Adrián Ghajari Espinosa, Victor Fresno,
• Abstract summary: This dataset consists of 1003 multiple-choice questions of university entrance level exams in Spanish and English.<n>A selection of current open-source and proprietary models are evaluated in a uniform zero-shot experimental setting.
• Score: 35.88131356701857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this article we present UNED-ACCESS 2024, a bilingual dataset that consists of 1003 multiple-choice questions of university entrance level exams in Spanish and English. Questions are originally formulated in Spanish and translated manually into English, and have not ever been publicly released. A selection of current open-source and proprietary models are evaluated in a uniform zero-shot experimental setting both on the UNED-ACCESS 2024 dataset and on an equivalent subset of MMLU questions. Results show that (i) reasoning questions are challenging for models, (ii) smaller models perform worse than larger models and degrade faster in Spanish than in English and (iii) the performance gap between languages is negligible for the best models and grows up to 37% for smaller models. Model ranking on UNED-ACCESS 2024 is almost identical in English and Spanish, and has also a high correlation (0.98 Pearson) with ranking on MMLU, suggesting that a small dataset is sufficiently diverse and representative to measure performance by discipline.

Related papers

• Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages [9.426642998924724]
  Multilingual large language models generate non-faithful output in resource-constrained languages. To mitigate unfaithfulness in such settings, we propose using computationally light auxiliary models to rescore the outputs of larger architectures. We show that monolingual 4-layer BERT models pretrained from scratch on less than 700 MB of data without fine-tuning are able to identify faithful summaries with a mean accuracy of 88.33%.
  arXiv  Detail & Related papers  (2025-02-24T21:22:19Z)
• Linguini: A benchmark for language-agnostic linguistic reasoning [37.73108306825993]
  We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge. The test covers 894 questions grouped in 160 problems across 75 (mostly) extremely low-resource languages. We find that while all analyzed models rank below 25% accuracy, there is a significant gap between open and closed models.
  arXiv  Detail & Related papers  (2024-09-18T16:51:02Z)
• HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation [0.8083061106940517]
  This paper summarizes the experiments and results of the HYBRINFOX team for the CheckThat! 2024 - Task 1 competition. We propose an approach enriching Language Models such as RoBERTa with embeddings produced by triples.
  arXiv  Detail & Related papers  (2024-07-04T11:33:54Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• SurreyAI 2023 Submission for the Quality Estimation Shared Task [17.122657128702276]
  This paper describes the approach adopted by the SurreyAI team for addressing the Sentence-Level Direct Assessment task in WMT23. The proposed approach builds upon the TransQuest framework, exploring various autoencoder pre-trained language models. The evaluation utilizes Spearman and Pearson correlation coefficients, assessing the relationship between machine-predicted quality scores and human judgments.
  arXiv  Detail & Related papers  (2023-12-01T12:01:04Z)
• Assessing Translation capabilities of Large Language Models involving English and Indian Languages [4.067706269490143]
  We explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We fine-tune these large language models using parameter efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as CHRF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively.
  arXiv  Detail & Related papers  (2023-11-15T18:58:19Z)
• 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)
• Lessons learned from the evaluation of Spanish Language Models [27.653133576469276]
  We present a head-to-head comparison of language models for Spanish with the following results. We argue for the need of more research to understand the factors underlying them. The recent activity in the development of language technology for Spanish is to be welcomed, but our results show that building language models remains an open, resource-heavy problem.
  arXiv  Detail & Related papers  (2022-12-16T10:33:38Z)
• SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages [102.50127671423752]
  We introduce SMaLL-100, a distilled version of the M2M-100 (12B) machine translation model covering 100 languages. We train SMaLL-100 with uniform sampling across all language pairs and therefore focus on preserving the performance of low-resource languages. Our model achieves comparable results to M2M-100 (1.2B), while being 3.6x smaller and 4.3x faster at inference.
  arXiv  Detail & Related papers  (2022-10-20T22:32:29Z)
• Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases [55.45617404586874]
  We propose a few-shot instruction-based method for prompting pre-trained language models (LMs) We show that large LMs can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models.
  arXiv  Detail & Related papers  (2021-12-15T04:19:52Z)
• Multilingual Answer Sentence Reranking via Automatically Translated Data [97.98885151955467]
  We present a study on the design of multilingual Answer Sentence Selection (AS2) models, which are a core component of modern Question Answering (QA) systems. The main idea is to transfer data, created from one resource rich language, e.g., English, to other languages, less rich in terms of resources.
  arXiv  Detail & Related papers  (2021-02-20T03:52:08Z)

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.