Elamur Research⌕
☰
home / papers / 2026 / Proficiency-Controlled Text Simplification in European Portuguese: A Preliminary Study using Prompting Approaches

Proficiency-Controlled Text Simplification in European Portuguese: A Preliminary Study using Prompting Approaches

Summary

The paper addresses proficiency-controlled text simplification for European Portuguese, a variety where level-targeted rewriting has received far less attention than in English. The authors ask whether prompting alone can steer a compact LLM, GPT-5-nano, to produce text at a chosen difficulty, without fine-tuning, ensembles or multi-candidate generation. They take 40 texts from the most complex level of the iRead4Skills dataset, which was built for adult native speakers with low literacy. Each text is rewritten into three easier levels that roughly correspond to CEFR B1, A2 and A1. The authors compare zero-shot and few-shot setups that vary three factors: anchoring levels to CEFR, explicitly asking the model to keep the meaning, and supplying similar examples. A fine-tuned proficiency classifier and semantic similarity measures score the outputs, and human judges check them. The model reliably makes texts simpler but seldom hits the exact requested level. This suggests prompt engineering is insufficient for this language, and that model adaptation and stronger evaluation protocols are the next steps.

Key points

  • Data: 40 texts from the hardest of the four iRead4Skills complexity levels, simplified to plain, easy and very easy (≈ CEFR B1, A2, A1).
  • Model and prompting: GPT-5-nano. Few-shot examples are retrieved by semantic similarity, and the study tests the effects of CEFR anchoring and meaning-preservation instructions.
  • Evaluation: a fine-tuned textual complexity classifier for level, with BERTScore and document embeddings for meaning preservation, complemented by human assessment.
  • Results: exact target-level accuracy stays under 40%, while target-or-below accuracy peaks at 61.39%. Human judgments match the automatic trends but show how subjective level and meaning judgments are.
  • Resource: the simplified texts produced for the human evaluation form a small parallel corpus for future European Portuguese work.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Machine translation · Natural language processing

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/4sw76nrnosj6

@inproceedings{ribeiro2026proficiency,
  title = {{Proficiency-Controlled Text Simplification in European Portuguese: A Preliminary Study using Prompting Approaches}},
  author = {Ribeiro, Eugénio and Antunes, David and Mamede, Nuno and Baptista, Jorge},
  booktitle = {Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026},
  year = {2026},
  doi = {10.63317/4sw76nrnosj6},
  url = {https://doi.org/10.63317/4sw76nrnosj6}
}

References

63 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sweta Agrawal and Marine Carpuat. 2023. Controlling Pre-trained Language Models for Grade-Specific Text Simplification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 12807– 12819. ↗
  2. Wafa Aissa, Raquel Amaro, David Antunes, Thibault Bañeras-Roux, Jorge Baptista, Alejandro Catala, Luís Correia, Thomas François, Marcos Garcia, Mario Izquierdo-Álvarez, Nuno Mamede, Vasco Martins, Miguel Neves, Eugénio Ribeiro, Sandra Rodriguez, and Elodie Vanz-ereven. 2025. The iRead4Skills Intelligent Complexity Analyzer. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations, pages 73–84. find
  3. Sandra Maria Aluísio, Lucia Specia, Thiago Alexandre Salgueiro Pardo, Erick Galani Maziero, Helena De Medeiros Caseli, and Renata Pontin de Mattos Fortes. 2008a. A Corpus Analysis of Simple Account Texts and the Proposal of Simplification Strategies: First Steps Towards Text Simplification Systems. In Proceedings of the Annual ACM International Conference on Design of Communication (SIGDOC), pages 15–22. find
  4. Sandra Maria Aluísio, Lucia Specia, Thiago Alexandre Salgueiro Pardo, Erick Galani Maziero, and Renata Pontin de Mattos Fortes. 2008b. Towards Brazilian Portuguese Automatic Text Simplification Systems. In Proceedings of ACM Symposium on Document Engineering (DocEng), pages 240–248. find
  5. Fernando Alva-Manchego, Louis Martin, Antoine Bordes, Carolina Scarton, Benoît Sagot, and Lucia Specia. 2020. ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 4668–4679. find our card
  6. Fernando Alva-Manchego, Regina Stodden, Joseph Marvin Imperial, Abdullah Barayan, Kai North, and Harish Tayyar Madabushi. 2025. Findings of the TSAR 2025 Shared Task on Readability-Controlled Text Simplification. In Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR), pages 116–130. find
  7. Alexandre Alves, Péricles B.C. Miranda, Rafael Ferreira Mello, and André Nascimento. 2023. Automatic Simplification of Legal Texts in Portuguese Using Machine Learning. Frontiers in Artificial Intelligence and Applications, 379:281–286. ↗
  8. Marcelo Adriano Amancio, Magali Sanches Duran, and Sandra Maria Aluí́sio. 2011. Automatic Question Categorization: A new Approach for Text Elaboration. Procesamiento del Lenguaje Natural, 46:43–50. find
  9. Abdullah Barayan, Jose Camacho-Collados, and Fernando Alva-Manchego. 2025. Analysing Zero-Shot Readability-Controlled Sentence Simplification. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 6762–6781. ↗
  10. David Beauchemin, Horacio Saggion, and Richard Khoury. 2023. MeaningBERT: Assessing Meaning Preservation between Sentences. Frontiers in Artificial Intelligence, 6. ↗
  11. António Branco, João Rodrigues, Francisco Costa, João Silva, and Rui Vaz. 2014. Assessing Automatic Text Classification for Interactive Language Learning. In Proceedings of the International Conference on Information Society (i-Society), pages 70–78. find
  12. Arnaldo Cândido Junior, Ann Copestake, Lucia Specia, and Sandra Maria Aluísio. 2011. Towards an on-demand Simple Portuguese Wikipedia. Workshop on Speech and Language Processing for Assistive Technologies (SLPAT), pages 137–147. find
  13. Arnaldo Cândido Junior, Matheus de Oliveira, and Sandra Maria Aluísio. 2009a. Simplifica: A Simplified Texts Web Authoring System. In Proceedings of the Brazilian Symposium on Multimedia and the Web (WebMedia). find
  14. Arnaldo Cândido Junior, Erick Maziero, Caroline Gasperin, Thiago Alexandre Salgueiro Pardo, Lucia Specia, and Sandra Maria Aluísio. 2009b. Supporting the Adaptation of Texts for Poor Literacy Readers: A Text Simplification Editor for Brazilian Portuguese. In Proceedings of the Workshop on Innovative Use of NLP for Building Educational Applications (BEA), pages 34–42. find
  15. Diedre Carmo, Marcos Piau, Israel Campiotti, Rodrigo Nogueira, and Roberto Lotufo. 2020. PTT5: Pretraining and Validating the T5 Model on Brazilian Portuguese Data. Computing Research Repository, arXiv:2008.09144. ↗
  16. Jacob Cohen. 1960. A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement, 20(1):37–46. ↗
  17. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised Cross-lingual Representation Learning at Scale. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 8440–8451. find
  18. Council of Europe. 2001. Common European Framework of Reference for Languages: Learning, Teaching, Assessment. Cambridge University Press. find
  19. Pedro Curto. 2014. Classificador de Textos para o Ensino de Português como Segunda Língua. Master’s thesis, Instituto Superior Técnico, Universidade de Lisboa. find
  20. Tiago B. de Lima, André C. A. Nascimento, George Valença, Pericles Miranda, Rafael Ferreira Mello, and Tapas Si. 2021. Portuguese Neural Text Simplification Using Machine Translation. In Proceedings of the Brazilian Conference on Intelligent Systems (BRACIS), pages 542–556. find
  21. Asma Farajidizaji, Vatsal Raina, and Mark Gales. 2024. Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models. In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9325–9339. find
  22. Daniel Ferrés, Horacio Saggion, and Xavier Gómez Guinovart. 2017. An Adaptable Lexical Simplification Architecture for Major Ibero-Romance Languages. In Proceedings of the Workshop on Building Linguistically Generalizable NLP Systems, pages 40–47. find
  23. Maria José Bocorny Finatto and Lucas Meireles Tcacenco. 2021. Intralingual Translation, Equivalence Strategies and Textual and Terminological Accessibility. TradTerm, 37(1):30–63. find
  24. Luís Gomes, António Branco, João Silva, João Rodrigues, and Rodrigo Santos. 2025. Open Sentence Embeddings for Portuguese with the Serafim PT* Encoders Family. In Proceedings of the EPIA Conference on Artificial Intelligence, pages 267–279. find
  25. Akio Hayakawa, Nouran Khallaf, Horacio Saggion, and Serge Sharoff. 2025. UoL-UPF at TSAR 2025 Shared Task: A Generate-and-Select Approach for Readability-Controlled Text Simplification. In Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR), pages 193–210. find
  26. Andrew F. Hayes and Klaus Krippendorff. 2007. Answering the Call for a Standard Reliability Measure for Coding Data. Communication Methods and Measures, 1(1):77–89. ↗
  27. Joseph Marvin Imperial, Abdullah Barayan, Regina Stodden, Rodrigo Wilkens, Ricardo Muñoz Sánchez, Lingyun Gao, Melissa Torgbi, Dawn Knight, Gail Forey, Reka R. Jablonkai, Ekaterina Kochmar, Robert Joshua Reynolds, Eugénio Ribeiro, Horacio Saggion, Elena Volodina, Sowmya Vajjala, Thomas François, Fernando Alva-Manchego, and Harish Tayyar Madabushi. 2025. UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9703–9755. find
  28. Joseph Marvin Imperial and Harish Tayyar Madabushi. 2023. Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models. In Proceedings of the Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 205–223. find
  29. Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, and Wei Xu. 2020. Neural CRF Model for Sentence Alignment in Text Simplification. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 7943–7960. find our card
  30. J. Peter Kincaid, Robert P. Fishburne Jr, Richard L. Rogers, and Brad S. Chissom. 1975. Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel. Technical report, Institute for Simulation and Training, University of Central Florida. ↗
  31. Sidney Evaldo Leal, Magali Sanches Durán, and Sandra Maria Aluísio. 2018. A Nontrivial Sentence Corpus for the Task of Sentence Readability Assessment in Portuguese. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 401–413. find
  32. Jiawei Li, Yang Gao, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, Yiguan Lin, Bin Xu, Bowen Ren, Chong Feng, and Heyan Huang. 2025. Fundamental Capabilities and Applications of Large Language Models: A Survey. ACM Computing Surveys, 58(2). ↗ our card
  33. Ali Malik, Stephen Mayhew, Christopher Piech, and Klinton Bicknell. 2024. From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation. In Findings of the Association for Computational Linguistics: ACL, pages 15670–15693. find
  34. Louis Raphaël Théo Martin, Angela Fan, Éric de la Clergerie, Antoine Bordes, and Benoît Sagot. 2022. MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases. In Proceedings of the Language Resources and Evaluation Conference (LREC), pages 1651– 1664. find our card
  35. Rina Miyata, Koki Horiguchi, Risa Kondo, Yuki Fujiwara, and Tomoyuki Kajiwara. 2025. EhiMeNLP at TSAR 2025 Shared Task: Candidate Generation via Iterative Simplification and Reranking by Readability and Semantic Similarity. In Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR 2025), pages 217–222. find
  36. Ricardo Monteiro, Raquel Amaro, Susana Correia, Alice Pintard, Roser Gauchola, Michell Moutinho, and Xavier Blanco Escoda. 2023. iRead4Skills Complexity Levels. Project Deliverable D3.1, iRead4Skills. ↗
  37. Daiki Nishihara, Tomoyuki Kajiwara, and Yuki Arase. 2019. Controllable Text Simplification with Lexical Constraint Loss. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop, pages 260–266. ↗
  38. Fernando A. A. Nóbrega, Alipio M. Jorge, Pavel Brazdil, and Thiago A. S. Pardo. 2020. Sentence Compression for Portuguese. In Proceedings of the International Conference on Computational Processing of Portuguese (PROPOR), pages 270–280. find
  39. Kai North, Tharindu Ranasinghe, Matthew Shardlow, and Marcos Zampieri. 2024. MultiLS: An End-to-End Lexical Simplification Framework. In Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR), pages 1–11. find
  40. OpenAI. 2025. GPT-5 System Card. Computing Research Repository, arXiv:2601.03267. ↗ our card
  41. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 311–318. find our card
  42. Francielle Vasconcellos Pereira, Ana Paula Rodrigues Feitosa Frazão, and Viviane Pereira Moreira. 2024. Automatic Text Simplification for the Legal Domain in Brazilian Portuguese. In Proceedings of the Brazilian Conference on Intelligent Systems (BRACIS), pages 31–45. find
  43. Alice Pintard, Thomas François, Justine Nagant de Deuxchaisnes, Sílvia Barbosa, Maria Leonor Reis, Michell Moutinho, Ricardo Monteiro, Raquel Amaro, Susana Correia, Sandra Rodríguez Rey, Marcos Garcia González, Keran Mu, and Xavier Blanco Escoda. 2024. iRead4Skills Dataset 1: Corpora by Complexity Level for FR, PT and SP. Project Deliverable D3.2, iRead4Skills. find
  44. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992. find
  45. Maria Leonor Reis, Sílvia Barbosa, Michell Moutinho, Ricardo Monteiro, Susana Correia, and Raquel Amaro. 2024. Intelligent Support for Low Literacy Adults: The European Portuguese iRead4Skills Corpus. International Journal of Emerging Technologies in Learning (iJET), 19(8):61–81. ↗
  46. Eugénio Ribeiro, David Antunes, Nuno Mamede, and Jorge Baptista. 2025. Exploring Few-Shot Approaches to Automatic Text Complexity Assessment in European Portuguese. Journal of the Brazilian Computer Society, 31(1):690–710. ↗
  47. Eugénio Ribeiro, Nuno Mamede, and Jorge Baptista. 2024. Avaliação Automática do Nível de Complexidade de Textos em Português Europeu. Linguamática, 16(2):121–145. ↗
  48. Leonardo F. R. Ribeiro, Mohit Bansal, and Markus Dreyer. 2023. Generating Summaries with Controllable Readability Levels. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 11669– 11687. find
  49. Leandro Borges dos Santos, Magali Sanches Duran, Nathan Siegle Hartmann, Arnaldo Cândido Junior, Gustavo Henrique Paetzold, and Sandra Maria Aluísio. 2017. A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese. In Proceedings of the International Conference on Text, Speech, and Dialogue (TSD), pages 281–289. ↗
  50. Arthur Scalercio, Maria Finatto, and Aline Paes. 2024. Enhancing Sentence Simplification in Portuguese: Leveraging Paraphrases, Context, and Linguistic Features. In Findings of the Association for Computational Linguistics: ACL, pages 15076–15091. find
  51. Carolina Scarton and Lucia Specia. 2018. Learning Simplifications for Specific Target Audiences. In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL), volume 2: Short Papers, pages 712–718. find
  52. Mao Shimada, Kexin Bian, Zhidong Ling, and Mamoru Komachi. 2025. HIT-YOU at TSAR 2025 Shared Task: Leveraging Similarity-Based Few-Shot Prompting, Round-Trip Translation, and Self-Refinement for Readability-Controlled Text Simplification. In Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR), pages 231–241. find
  53. Fábio Souza, Rodrigo Nogueira, and Roberto Lotufo. 2020. BERTimbau: Pretrained BERT Models for Brazilian Portuguese. In Proceedings of the Brazilian Conference on Intelligent Systems (BRACIS), pages 403–417. find
  54. Lucia Specia. 2010. Translating from Complex to Simplified Sentences. In Proceedings of the International Conference on Computational Processing of Portuguese (PROPOR), pages 30–39. find
  55. Sanja Stajner. 2021. Automatic Text Simplification for Social Good: Progress and Challenges. In Findings of the Association for Computational Linguistics: ACL-IJCNLP, pages 2637–2652. ↗
  56. Satoru Uchida, Shohei Takada, and Yuki Arase. 2018. CEFR-based Lexical Simplification Dataset. In Proceedings of the International Conference on Language Resources and Evaluation (LREC), pages 3254–3258. find
  57. Rodrigo Wilkens, Leonardo Zilio, Silvio Ricardo Cordeiro, Felipe S.F. Paula, Carlos Ramisch, Marco A.P. Idiart, and Aline Villavicencio. 2017. LexSubNC: A Dataset of Lexical Substitution for Nominal Compounds. In Proceedings of the International Conference on Computational Semantics (IWCS), volume Short papers. find
  58. Wei Xu, Chris Callison-Burch, and Courtney Napoles. 2015. Problems in Current Text Simplification Research: New Data Can Help. Transactions of the Association for Computational Linguistics, 3:283–297. ↗ our card
  59. Wei Xu, Chris Callison-Burch, and Courtney Nápoles. 2016. Optimizing Statistical Machine Translation for Text Simplification. In Transactions of the Association for Computational Linguistics, volume 4, pages 401–415. ↗ our card
  60. Daiki Yanamoto, Tomoki Ikawa, Tomoyuki Kajiwara, Takashi Ninomiya, Satoru Uchida, and Yuki Arase. 2022. Controllable Text Simplification with Deep Reinforcement Learning. In Proceedings of the Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the International Joint Conference on Natural Language Processing (IJCNLP), volume 2: Short Papers, pages 398–404. find
  61. Tatsuya Zetsu, Tomoyuki Kajiwara, and Yuki Arase. 2022. Lexically Constrained Decoding with Edit Operation Prediction for Controllable Text Simplification. In Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR), pages 147–153. find
  62. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In Proceedings of the International Conference on Learning Representations (ICLR). ↗
  63. Yang Zhang, Hanlei Jin, Dan Meng, Jun Wang, and Jinghua Tan. 2026. A Comprehensive Survey on Automatic Text Summarization with Exploration of LLM-based Methods. Neurocomputing, 663:131928. ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/ribeiro-2026-proficiency-controlled-text-simplification-european/