AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

• URL: http://arxiv.org/abs/2603.26511v1
• Date: Fri, 27 Mar 2026 15:22:33 GMT
• Title: AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese
• Abstract summary: We introduce AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages.<n>We release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias.<n>Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations.
• Score: 12.322686257512428
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresented in both training data and native evaluation, with machine-translated benchmarks likely missing the variant's linguistic and cultural nuances. We introduce AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages. To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias. Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations, supporting the case for targeted training and native benchmarking for European Portuguese.

Related papers

• EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages [2.897376329231807]
  Machine translation can distort task-critical constraints and required outputs.<n>We introduce EuroAlpaca, a task-preserving localisation pipeline.<n>We show that preserving task semantics is essential for multilingual instruction tuning.
  arXiv  Detail & Related papers  (2026-09-04T12:05:53Z)
• Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders [42.78591555984395]
  Portuguese is one of the most widely spoken languages in the world.<n> embedding models are often selected based on English or multilingual metrics, while their effectiveness in Portuguese remains unclear.<n>We present MTEB-PT, a Portuguese benchmark constructed from a subset of MMTEB.
  arXiv  Detail & Related papers  (2026-07-05T01:06:29Z)
• AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model [6.462620395914082]
  AMALIA-VL is the first open-source instruction-tuned LVLM built for pt-PT.<n>We will release model weights, training data, and construction pipelines along with machine-translated pt-PT evaluation benchmarks to help democratize pt-PT LVLM development.
  arXiv  Detail & Related papers  (2026-06-17T14:11:41Z)
• PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction [7.442299103783346]
  European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages.<n>This work addresses modern OCR applications, introducing Por TEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction.<n>We observe a sharp performance drop from synthetic to real world samples in most models, and find that, currently, specialized multilingual data is a better driver for pt-PT performance than model size or resolution budget.
  arXiv  Detail & Related papers  (2026-06-17T14:06:26Z)
• ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation [63.89730738735446]
  We propose ReflectMT, a two-stage reflection internalization algorithm for machine translation.<n>Our approach develops the model's "translate-reflect-refine" capability through reinforcement learning.<n> Experimental results on datasets such as WMT24 demonstrate that our model's first-pass translations during inference outperform multi-step reasoning LRMs.
  arXiv  Detail & Related papers  (2026-04-21T06:48:41Z)
• ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs [6.876400358750551]
  We introduce ALBA, a benchmark designed to assess proficiency in linguistic-related tasks in European Portuguese (pt-PT)<n>ALBA is manually constructed by language experts and paired with an LLM-as-a-judge framework for scalable evaluation of pt-PT generated language.<n> Experiments on a diverse set of models reveal performance variability across linguistic dimensions, highlighting the need for comprehensive, variety-sensitive benchmarks.
  arXiv  Detail & Related papers  (2026-03-27T15:25:44Z)
• EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training [8.56742227411733]
  Large language models (LLMs) are predominantly trained on English-centric data, resulting in uneven performance for smaller languages.<n>We study whether continued pretraining (CPT) can substantially improve Estonian capabilities in a pretrained multilingual LLM.
  arXiv  Detail & Related papers  (2026-03-02T16:24:36Z)
• Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets [2.0199251985015434]
  We present a fully automated framework designed to enable scalable, high-quality translation of datasets and benchmarks.<n>We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages.
  arXiv  Detail & Related papers  (2026-02-25T18:58:25Z)
• PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning [54.19784655270799]
  We introduce textbfPEGRL, a textittwo-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.<n>Experiments on English$to$Finnish, English$to$Turkish, and English$leftrightarrow$Chinese show consistent gains over RL baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:22:55Z)
• Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda [0.0]
  We explore the application of Back translation as a semi-supervised technique to enhance Neural Machine Translation models for the English-Luganda language pair.<n>Our methodology involves developing custom NMT models using both publicly available and web-crawled data, and applying Iterative and Incremental Back translation techniques.<n>The results of our study show significant improvements, with translation performance for the English-Luganda pair exceeding previous benchmarks by more than 10 BLEU score units across all translation directions.
  arXiv  Detail & Related papers  (2025-05-05T08:47:52Z)
• 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)
• Adapting Large Language Models for Document-Level Machine Translation [46.370862171452444]
  Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs.
  arXiv  Detail & Related papers  (2024-01-12T09:29:13Z)
• LLaMA Beyond English: An Empirical Study on Language Capability Transfer [49.298360366468934]
  We focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. We employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench.
  arXiv  Detail & Related papers  (2024-01-02T06:29:02Z)
• Extrapolating Large Language Models to Non-English by Aligning Languages [109.09051737966178]
  Existing large language models show disparate capability across different languages. In this paper, we empower pre-trained LLMs on non-English languages by building semantic alignment across languages.
  arXiv  Detail & Related papers  (2023-08-09T13:32:06Z)
• Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task [80.22825549235556]
  We present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE. Specifically, our systems employ the framework of UniTE, which combined three types of input formats during training with a pre-trained language model. Results show that our models reach 1st overall ranking in the Multilingual and English-Russian settings, and 2nd overall ranking in English-German and Chinese-English settings.
  arXiv  Detail & Related papers  (2022-10-18T08:55:27Z)
• Improving Multilingual Translation by Representation and Gradient Regularization [82.42760103045083]
  We propose a joint approach to regularize NMT models at both representation-level and gradient-level. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance.
  arXiv  Detail & Related papers  (2021-09-10T10:52:21Z)

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.