--- title: "Lispector — paper by Medeiros et al. (2026) — summary and ideas" description: "Production proofreading tools for Brazilian Portuguese need corrections that are predictable and minimal, without… 83% BLEU. 1 reference." authors: ["Andresa Medeiros", "Felipe Iszlaji", "Claudia Sarmiento-Moreno", "Camila Muniz", "Larissa Ponciano", "Larissa Dejigov", "Ronald Monteiro", "Pedro Kretikouski", "Guilherme Chaves"] year: 2026 venue: "Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2" source: "https://aclanthology.org/2026.propor-2.8/" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" title_orig: "Lispector: Fine-tuning de Modelos de Linguagem para Revisão Gramatical e Ortográfica em Português Brasileiro" title_lang: "pt" canonical: "https://research.elamur.ai/free/en/papers/medeiros-2026-lispector-fine-tuning-de-modelos/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/medeiros-2026-lispector-fine-tuning-de-modelos/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/) / Lispector: fine-tuning language models for grammar and spelling correction in Brazilian Portuguese # Lispector: fine-tuning language models for grammar and spelling correction in Brazilian Portuguese *Original (Portuguese): Lispector: Fine-tuning de Modelos de Linguagem para Revisão Gramatical e Ortográfica em Português Brasileiro* **Authors:** Andresa Medeiros, Felipe Iszlaji, Claudia Sarmiento-Moreno, Camila Muniz, Larissa Ponciano, Larissa Dejigov, Ronald Monteiro, Pedro Kretikouski and Guilherme Chaves · **Year:** 2026 · **Venue:** [Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2](https://md.research.elamur.ai/free/en/venues/propor/) ([International Conference on Computational Processing of Portuguese 2026](https://md.research.elamur.ai/free/en/venues/propor/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.propor-2.8/) · [PDF](https://aclanthology.org/2026.propor-2.8.pdf) ## Summary Production proofreading tools for Brazilian Portuguese need corrections that are predictable and minimal, without unnecessary rewriting. The authors, from the company Clarice.ai, ask whether smaller fine-tuned LLMs can match or beat larger general-purpose models used only with few-shot prompting. They built Lispector, two supervised fine-tuned models: Lispector large, based on GPT-4.1, and Lispector small, based on GPT-4.1 nano. Training used 4,500 pairs of real user texts from Clarice.ai, each with a reference correction written by linguists. The baselines were GPT-5, GPT-4.1, GPT-5 nano and GPT-4.1 nano, all given the same few-shot prompts. Both Lispector variants beat every baseline on BLEU, GLEU, METEOR and ROUGE. The small variant scored about as well as the large one. Lispector small also had the lowest median latency of all models tested, while GPT-5 models took tens of seconds per request. The study suggests that task-specific fine-tuning of compact models is the better trade-off when cost and latency matter. However, the models, data and prompts are proprietary and have not been released. ## Key points - **Dataset:** 4,500 original/corrected pairs from real Clarice.ai users, split into 2,500 for training, 1,000 for validation and 1,000 for testing, with no overlap. The average record is about 130 tokens. - **Training setup:** both models used 3 epochs, batch size 6 and a learning-rate multiplier of 0.1. Lispector small was trained on about 792,000 tokens. - **Quality:** both Lispector models reached 83% BLEU and 89% GLEU, against 70–77% and 77–81% for the prompted baselines. This is a gain of up to +13 BLEU and +12 GLEU. They also scored 97% on METEOR and ROUGE-1 and 89–90% on ROUGE-2. - **Latency:** Lispector small had a median of 1,378 ms and a P95 of 2,601 ms, and Lispector large had a median of 2,040 ms. GPT-5 had a median of about 41 s and a P95 of about 163 s. - **Limitations:** the paper includes no comparison with LanguageTool and did not optimize the baseline prompts. Evaluation relied only on automatic metrics, with no human assessment. Lispector is already in production on Clarice.ai. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works 🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🖍️ Grammatical error correction & learner language](https://md.research.elamur.ai/free/en/topics/grammatical-error-correction/) · 162 works ## Cite Cite as: Andresa Medeiros, Felipe Iszlaji, Claudia Sarmiento-Moreno, Camila Muniz, Larissa Ponciano, Larissa Dejigov, Ronald Monteiro, Pedro Kretikouski and Guilherme Chaves. 2026. Lispector: Fine-tuning de Modelos de Linguagem para Revisão Gramatical e Ortográfica em Português Brasileiro. Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{medeiros2026lispector, title = {{Lispector: Fine-tuning de Modelos de Linguagem para Revisão Gramatical e Ortográfica em Português Brasileiro}}, author = {Andresa Medeiros, Felipe Iszlaji, Claudia Sarmiento-Moreno, Camila Muniz, Larissa Ponciano, Larissa Dejigov, Ronald Monteiro, Pedro Kretikouski and Guilherme Chaves}, booktitle = {Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2}, year = {2026}, url = {https://aclanthology.org/2026.propor-2.8/} } ``` - [← previous LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points](https://md.research.elamur.ai/free/en/papers/zhang-2026-linkqa-synthesizing-diverse-qa-multiple/) - [next → Listening for Ideology: Automatic Analysis of Character Speech in Historical Nazi Propaganda Films](https://md.research.elamur.ai/free/en/papers/ruth-2026-listening-ideology-automatic-analysis-character/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work. 1. Satanjeev Banerjee and Alon Lavie. 2005. [METEOR: An automatic metric for MT evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Transla- *Updated 1 November 2026*