Elamur Research⌕
☰
home / papers / 2026 / Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources

Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources

Summary

Controlled sentence simplification means rewriting a sentence so that it reaches a requested difficulty level. It depends on parallel data labelled with readability, and such data is scarce outside English. The authors address this gap for Italian by building IMPaCTS, a parallel simplification corpus spanning multiple difficulty levels, without any manual annotation. They compared three Italian-tuned LLMs on zero-shot simplification and chose LLaMAntino-2. They then ran it with Divergent Beam Search to produce several alternative simplifications for sentences from Wikipedia and from the administrative corpus PaWaC. Each pair was scored with the READ-IT readability tool and profiled with 144 linguistic features. Simplifications were then ranked by readability within each source sentence. Growing subsets of the corpus were used to fine-tune six open-weight mono- and multilingual LLMs, which receive a target readability value together with the input. In automatic and human evaluations, the fine-tuned models completed the task better and matched the requested readability more closely than few-shot baselines. The work provides a reusable resource and recipe for languages with few simplification datasets, along with evidence on how training-data size affects results.

Key points

  • IMPaCTS contains 1,444,160 original–simple pairs: 1,058,960 from Wikipedia (~100,000 source sentences) and 385,200 from PaWaC (~40,000 source sentences). After duplicate removal, each source has 2–10 simplifications, averaging 9.6.
  • The generator was selected on 1,212 test pairs from SIMPITIKI, PaCCSS–IT, Terence, Teacher and ADMIN-it. LLaMAntino-2 outperformed ANITA and Italia, reaching SARI 40.99, BLEU 0.18 and BERTScore 0.81.
  • Decoding used Divergent Beam Search with 20 beams in 10 groups and a diversity penalty of λ = 0.7. This setting was chosen by manual inspection as the best trade-off between diversity and fluency.
  • Readability levels come from READ-IT rankings computed per source sentence. Five representative simplifications (s_1 to s_5) were kept for each source. Sentence splitting was infrequent, averaging 1.31 splits in Wikipedia and 1.47 in PaWaC.
  • During fine-tuning and prompting, the target is passed as a numeric readability value from 0 to 100. The corpus and an exploration notebook are released on GitHub (michelepapucci/impacts).

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: Linguistics & languages · Machine translation

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5fgm358dfxt5

@inproceedings{papucci2026controllable,
  title = {{Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources}},
  author = {Papucci, Michele and Venturi, Giulia and Dell'Orletta, Felice},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5fgm358dfxt5},
  url = {https://doi.org/10.63317/5fgm358dfxt5}
}

References

48 references, 9 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 2023 Conference on Empirical Methods in Natural Language Processing, pages 12807–12819, Singapore. Association for Computational Linguistics. ↗
  2. Sweta Agrawal, Weijia Xu, and Marine Carpuat. 2021. A non-autoregressive edit-based approach to controllable text simplification. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3757–3769, Online. Association for Computational Linguistics. find
  3. Abdullah Barayan, Jose Camacho-Collados, and Fernando Alva-Manchego. 2025. Analysing zero-shot readability-controlled sentence simplification. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6762–6781, Abu Dhabi, UAE. Association for Computational Linguistics. ↗
  4. Michele Cortelazzo. 2021. Il linguaggio amministrativo: principi e pratiche di modernizzazione. Carocci. find
  5. 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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9325– 9339, Torino, Italia. ELRA and ICCL. find
  6. Lyn Frazier. 1985. Syntactic complexity. In D.R. Dowty, L. Karttunen, and A.M. Zwicky, editors, Natural Language Parsing. Cambridge University Press, Cambridge, UK. find
  7. Martin Haspelmath. 2006. Against markedness (and what to replace it with). Journal of Linguistics, 42(1):25–70. ↗
  8. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3. find
  9. Tannon Kew, Alison Chi, Laura Vásquez-Rodríguez, Sweta Agrawal, Dennis Aumiller, Fernando Alva-Manchego, and Matthew Shardlow. 2023. BLESS: Benchmarking large language models on sentence simplification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13291–13309, Singapore. Association for Computational Linguistics. find
  10. Tannon Kew and Sarah Ebling. 2022. Target-level sentence simplification as controlled paraphrasing. In Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), pages 28–42, Abu Dhabi, United Arab Emirates (Virtual). Association for Computational Linguistics. ↗
  11. Zihao Li and Matthew Shardlow. 2024. How do control tokens affect natural language generation tasks like text simplification. Natural Language Engineering, 30(5):915–942. ↗
  12. Louis Martin, Éric de la Clergerie, Benoît Sagot, and Antoine Bordes. 2020. Controllable sentence simplification. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4689–4698, Marseille, France. European Language Resources Association. ↗
  13. Martina Miliani, Fernando Alva-Manchego, and Alessandro Lenci. 2023. Simplifying administrative texts for Italian L2 readers with controllable transformers models: A data-driven approach. In Proceedings of the 9th Italian Conference on Computational Linguistics (CLiC-it 2023), pages 303–315, Venice, Italy. CEUR Workshop Proceedings. find
  14. Daiki Nishihara, Tomoyuki Kajiwara, and Yuki Arase. 2019. Controllable text simplification with lexical constraint loss. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 260–266, Florence, Italy. Association for Computational Linguistics. ↗
  15. Debora Nozza and Giuseppe Attanasio. 2023. Is it really that simple? prompting large language models for automatic text simplification in Italian. In Proceedings of the 9th Italian Conference on Computational Linguistics (CLiC-it 2023), pages 322–333, Venice, Italy. CEUR Workshop Proceedings. find
  16. Alessio Palmero Aprosio, Sara Tonelli, Marco Turchi, Matteo Negri, and Mattia A. Di Gangi. 2019. Neural text simplification in low-resource conditions using weak supervision. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pages 37–44, Minneapolis, Minnesota. Association for Computational Linguistics. find
  17. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics. ↗ our card
  18. Michele Papucci, Giulia Venturi, and Felice Dell’Orletta. 2025. Generating and evaluating multi-level text simplification: A case study on Italian. In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), pages 870–885, Cagliari, Italy. CEUR Workshop Proceedings. find
  19. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. find
  20. Nils Reimers and Iryna Gurevych. 2020. Making monolingual sentence embeddings multilingual using knowledge distillation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. find our card
  21. Marco Russodivito, Vittorio Ganfi, Giuliana Fiorentino, and Rocco Oliveto. 2024. AI vs. human: Effectiveness of LLMs in simplifying Italian administrative documents. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 842–853, Pisa, Italy. CEUR Workshop Proceedings. find
  22. Michael J Ryan, Tarek Naous, and Wei Xu. 2023. Revisiting non-English text simplification: A unified multilingual benchmark. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4898–4927, Toronto, Canada. Association for Computational Linguistics. find
  23. Horacio Saggion. 2017. Automatic Text Simplification. Synthesis Lectures on Human Language Technologies. Morgan and Claypool. ↗
  24. Arthur Mariano Rocha De Azevedo Scalercio, Elvis A. De Souza, Maria José Bocorny Finatto, and Aline Paes. 2025. Evaluating LLMs for Portuguese sentence simplification with linguistic insights. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24452– 24477, Vienna, Austria. Association for Computational Linguistics. find
  25. Carolina Scarton and Lucia Specia. 2018. Learning simplifications for specific target audiences. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 712–718, Melbourne, Australia. Association for Computational Linguistics. find
  26. Kim Cheng Sheang, Daniel Ferrés, and Horacio Saggion. 2022. Controllable lexical simplification for English. In Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), pages 199–206, Abu Dhabi, United Arab Emirates (Virtual). Association for Computational Linguistics. find
  27. Nicolas Spring, Annette Rios, and Sarah Ebling. 2021. Exploring German multi-level text simplification. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1339– 1349, Held Online. INCOMA Ltd. find
  28. Ashwin K. Vijayakumar, Michael Cogswell, Ramprasaath R. Selvaraju, Qing Sun, Stefan Lee, David J. Crandall, and Dhruv Batra. 2016. Diverse beam search: Decoding diverse solutions from neural sequence models. CoRR, abs/1610.02424. ↗ our card
  29. Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch. 2016. Optimizing statistical machine translation for text simplification. Transactions of the Association for Computational Linguistics, 4:401–415. ↗ our card
  30. 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 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 398–404, Online only. Association for Computational Linguistics. find
  31. 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-2022), pages 147–153, Abu Dhabi, United Arab Emirates (Virtual). Association for Computational Linguistics. find
  32. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations. 10. ↗
  33. Language Resource References Yuki Arase, Satoru Uchida, and Tomoyuki Kajiwara. 2022. CEFR-based sentence difficulty annotation and assessment. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6206–6219, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  34. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Shengguang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Shusheng Yang, Yang Yao, Bowen Yu, Hongyi Yuan, Zheng Yuan, Jianwei Zhang, Xingxuan Zhang, Yichang Zhang, Zhenru Zhang, Chang Zhou, Jingren Zhou, Xiaohuan Zhou, and Tianhang Zhu. 2023. Qwen technical report. ↗ our card
  35. Pierpaolo Basile, Elio Musacchio, Marco Polignano, Lucia Siciliani, Giuseppe Fiameni, and Giovanni Semeraro. 2023. Llamantino: Llama 2 models for effective text generation in italian language. ↗
  36. Dominique Brunato, Andrea Cimino, Felice Dell’Orletta, and Giulia Venturi. 2016. PaCCSS-IT: A parallel corpus of complex-simple sentences for automatic text simplification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 351–361, Austin, Texas. Association for Computational Linguistics. find
  37. Dominique Brunato, Andrea Cimino, Felice Dell’Orletta, Giulia Venturi, and Simonetta Montemagni. 2020. Profiling-UD: a tool for linguistic profiling of texts. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 7145–7151, Marseille, France. European Language Resources Association. find
  38. Dominique Brunato, Felice Dell’Orletta, Giulia Venturi, and Simonetta Montemagni. 2015. Design and annotation of the first Italian corpus for text simplification. In Proceedings of the 9th Linguistic Annotation Workshop, pages 31–41, Denver, Colorado, USA. Association for Computational Linguistics. find
  39. Marie-Catherine De Marneffe, Christopher D Manning, Joakim Nivre, and Daniel Zeman. 2021. Universal dependencies. Computational linguistics, 47(2):255–308. find our card
  40. Felice Dell’Orletta, Simonetta Montemagni, and Giulia Venturi. 2011. READ–IT: Assessing readability of Italian texts with a view to text simplification. In Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies, pages 73–83, Edinburgh, Scotland, UK. Association for Computational Linguistics. find our card
  41. Louis 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 Thirteenth Language Resources and Evaluation Conference, pages 1651–1664, Marseille, France. European Language Resources Association. find our card
  42. Martina Miliani, Serena Auriemma, Fernando Alva-Manchego, and Alessandro Lenci. 2022. Neural readability pairwise ranking for sentences in Italian administrative language. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 849–866, Online only. Association for Computational Linguistics. find
  43. Riccardo Orlando, Luca Moroni, Pere-Lluís Huguet Cabot, Simone Conia, Edoardo Barba, Sergio Orlandini, Giuseppe Fiameni, and Roberto Navigli. 2024. Minerva LLMs: The first family of large language models trained from scratch on Italian data. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 707–719, Pisa, Italy. CEUR Workshop Proceedings. find
  44. Lucia C. Passaro and Alessandro Lenci. 2019. PaWaC - Public Administration Web as Corpus (Processed). http://data.europa.eu/88u/dataset/elrc_1282. [Data set]. ↗
  45. Marco Polignano, Pierpaolo Basile, and Giovanni Semeraro. 2024. Advanced natural-based interaction for the italian language: Llamantino-3-anita. find
  46. Sara Tonelli, Alessio Palmero Aprosio, and Francesca Saltori. 2016. Simpitiki: a simplification corpus for italian. Proceedings of CLiC-it. find
  47. 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
  48. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 483–498, Online. Association for Computational Linguistics. ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/papucci-2026-controllable-sentence-simplification-italian-fine/