---
title: "MioFFAn — paper by Ruiz et al. (2026) — summary and ideas"
description: "To help create such data, the authors release MioFFAn, an open-source annotation tool built on MioGatto. 35 references."
authors: ["Nicolas Sibuet Ruiz", "Horacio Saggion", "Riccardo Rossi"]
year: 2026
venue: "Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026"
source: "https://aclanthology.org/2026.nslp-1.20/"
doi: "10.63317/4s56b6f4i3u9"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ruiz-2026-mioffan-annotation-software-formula-formalization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ruiz-2026-mioffan-annotation-software-formula-formalization/)

[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/36/) / MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities

# MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities

**Authors:** Nicolas Sibuet Ruiz, [Horacio Saggion](https://md.research.elamur.ai/free/en/authors/horacio-saggion/) and Riccardo Rossi · **Year:** 2026 · **Venue:** [Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/nslp/) ([Natural Scientific Language Processing (NSLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/nslp/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.nslp-1.20/) · [PDF](https://aclanthology.org/2026.nslp-1.20.pdf) · [DOI 10.63317/4s56b6f4i3u9](https://doi.org/10.63317/4s56b6f4i3u9) · [OpenAlex](https://openalex.org/W7166569352)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Turning formulas in scientific papers into executable symbolic code, a task the authors call Formula Formalization, is held back by a lack of high-quality, domain-specific ground-truth data. To help create such data, the authors release MioFFAn, an open-source annotation tool built on MioGatto. MioGatto dealt with individual identifiers, their descriptions and coreference. MioFFAn instead targets whole expressions and keeps them inside the document. Annotators select a formula, describe its identifiers using taxonomies and properties they configure themselves, link those identifiers to the surrounding text, and then write the symbolic code using allowed CAS operators. The tool runs locally as a TypeScript/Python client-server web application over HTML+MathML.

Automation is modular. Sub-tasks with fixed output formats can be handed to LLMs and scored with standard NLP metrics, so annotators correct the model's output rather than starting from scratch. The authors configure the tool for Finite Element Methods (FEM) and run a proof-of-concept evaluation with small LLMs. The work matters because it makes it cheaper to build benchmarks and training corpora for formula-to-code systems in engineering and other technical fields.

## Key points
- MioFFAn (Math identifier-oriented Formula Formalization Annotator) is open-source and available at github.com/NicolasSR/MioFFAn. It extends MioGatto (Asakura et al., 2021).
- The annotation pipeline has four stages: formula selection, identifier characterization, contextual grounding and symbolic synthesis. Taxonomies and symbolic operators can be customized for each domain.
- The authors compared three ~4B models: NVIDIA-Nemotron-3-Nano-4B-BF16, gemma-3-4b-it and Qwen3-4B-Instruct-2507. On Symbol Segmentation, Qwen scored 57.7% coverage and 36.8% CoNLL. Nemotron scored 33.9% and 26.4%, and Gemma scored 28.2% and 18.8%.
- On Concept Assignment, all three models were close, with CoNLL between 95.6% and 98.0%. On SoG Identification, average SDI ranged from 14.9% to 18.3%. Qwen3-4B-Instruct-2507 was chosen for the proof-of-concept study.
- The FEM domain serves as the use case. The authors present it as evidence for the human-in-the-loop approach and consider their evaluation preliminary.

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

## Institutions

- [Universitat Politècnica de Catalunya](https://md.research.elamur.ai/free/en/universities/universitat-politecnica-de-catalunya/) — University, Barcelona, Spain · 31 works · 15,636 citations
- [Universitat Pompeu Fabra](https://md.research.elamur.ai/free/en/universities/universitat-pompeu-fabra/) — University, Barcelona, Spain · 47 works · 11,723 citations

Also on the byline: [International Center for Numerical Methods in Engineering](https://ror.org/03ej8a714).

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 252 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Nicolas Sibuet Ruiz, Horacio Saggion and Riccardo Rossi. 2026. MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities. Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ruiz2026mioffan,
  title = {{MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities}},
  author = {Nicolas Sibuet Ruiz, Horacio Saggion and Riccardo Rossi},
  booktitle = {Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026},
  year = {2026},
  doi = {10.63317/4s56b6f4i3u9},
  url = {https://doi.org/10.63317/4s56b6f4i3u9}
}
```

- [← previous Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers](https://md.research.elamur.ai/free/en/papers/barakat-2026-mining-pre-1948-palestinian-press/)
- [next → MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection](https://md.research.elamur.ai/free/en/papers/smiley-2026-miqrabert-regression-based-sentence-bert/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

35 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Maria Alexeeva, Rebecca Sharp, Marco A. Valenzuela-Escárcega, Jennifer Kadowaki, Adarsh Pyarelal, and Clayton Morrison. 2020. MathAlign: Linking formula identifiers to their contextual natural language descriptions. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 22… [find](https://scholar.google.com/scholar?q=Maria+Alexeeva%2C+Rebecca+Sharp%2C+Marco+A%2E+Valenzuela%2DEsc%C3%A1rcega%2C+Jennifer+Kadowaki%2C+Adarsh+Pyarelal%2C+and+Clayton+Morrison%2E+2020%2E+MathAlign%3A+Linking+formula+identifiers+to+their+contextual+natural+languag)
2. Takuto Asakura, Yusuke Miyao, Akiko Aizawa, and Michael Kohlhase. 2021. MioGatto: A math identifier-oriented grounding annotation tool. In Workshop Papers of the 14th Conference on Intelligent Computer Mathematics (CICM 2021), volume 3377 of CEUR Workshop Proceedings. CEUR-WS.org. [find](https://scholar.google.com/scholar?q=Takuto+Asakura%2C+Yusuke+Miyao%2C+Akiko+Aizawa%2C+and+Michael+Kohlhase%2E+2021%2E+MioGatto%3A+A+math+identifier%2Doriented+grounding+annotation+tool%2E+In+Workshop+Papers+of+the+14th+Conference+on+Intelligent+Compute)
3. Lukas Blecher, Guillem Cucurull, Thomas Scialom, and Robert Stojnic. 2023. Nougat: Neural Optical Understanding for Academic Documents. ArXiv:2308.13418 [cs]. [find](https://scholar.google.com/scholar?q=Lukas+Blecher%2C+Guillem+Cucurull%2C+Thomas+Scialom%2C+and+Robert+Stojnic%2E+2023%2E+Nougat%3A+Neural+Optical+Understanding+for+Academic+Documents%2E+ArXiv%3A2308%2E13418+%5Bcs%5D%2E)
4. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. 2023. Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks. ArXiv:2211.12588 [cs]. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Xueguang+Ma%2C+Xinyi+Wang%2C+and+William+W%2E+Cohen%2E+2023%2E+Program+of+Thoughts+Prompting%3A+Disentangling+Computation+from+Reasoning+for+Numerical+Reasoning+Tasks%2E+ArXiv%3A2211%2E12588+%5Bcs%5D%2E)
5. Pooyan Dadvand, Riccardo Rossi, and Eugenio Oñate. 2010. An Object-oriented Environment for Developing Finite Element Codes for Multidisciplinary Applications. Archives of Computational Methods in Engineering, 17(3):253–297. [find](https://scholar.google.com/scholar?q=Pooyan+Dadvand%2C+Riccardo+Rossi%2C+and+Eugenio+O%C3%B1ate%2E+2010%2E+An+Object%2Doriented+Environment+for+Developing+Finite+Element+Codes+for+Multidisciplinary+Applications%2E+Archives+of+Computational+Methods+in+Eng)
6. Aamin Dev, Takuto Asakura, and Rune Sætre. 2024. An approach to co-reference resolution and formula grounding for mathematical identifiers using large language models. In Proceedings of the 2nd Workshop on Mathematical Natural Language Processing @ LREC-COLING 2024, pages 1–10. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Aamin+Dev%2C+Takuto+Asakura%2C+and+Rune+S%C3%A6tre%2E+2024%2E+An+approach+to+co%2Dreference+resolution+and+formula+grounding+for+mathematical+identifiers+using+large+language+models%2E+In+Proceedings+of+the+2nd+Worksh)
7. André Greiner-Petter. 2023. Making Presentation Math Computable: A Context-Sensitive Approach for Translating LaTeX to Computer Algebra Systems. Springer Fachmedien, Wiesbaden. [find](https://scholar.google.com/scholar?q=Andr%C3%A9+Greiner%2DPetter%2E+2023%2E+Making+Presentation+Math+Computable%3A+A+Context%2DSensitive+Approach+for+Translating+LaTeX+to+Computer+Algebra+Systems%2E+Springer+Fachmedien%2C+Wiesbaden%2E)
8. André Greiner-Petter, Moritz Schubotz, Corinna Breitinger, Philipp Scharpf, Akiko Aizawa, and Bela Gipp. 2023. Do the Math: Making Mathematics in Wikipedia Computable. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4384–4395. [find](https://scholar.google.com/scholar?q=Andr%C3%A9+Greiner%2DPetter%2C+Moritz+Schubotz%2C+Corinna+Breitinger%2C+Philipp+Scharpf%2C+Akiko+Aizawa%2C+and+Bela+Gipp%2E+2023%2E+Do+the+Math%3A+Making+Mathematics+in+Wikipedia+Computable%2E+IEEE+Transactions+on+Pattern+Ana)
9. Mohammad R. Hashemi, Pavel B. Ryzhakov, and Riccardo Rossi. 2021. Three dimensional modeling of liquid droplet spreading on solid surface: An enriched finite element/level-set approach. Journal of Computational Physics, 442:110480. [find](https://scholar.google.com/scholar?q=Mohammad+R%2E+Hashemi%2C+Pavel+B%2E+Ryzhakov%2C+and+Riccardo+Rossi%2E+2021%2E+Three+dimensional+modeling+of+liquid+droplet+spreading+on+solid+surface%3A+An+enriched+finite+element%2Flevel%2Dset+approach%2E+Journal+of+Com)
10. Joy He-Yueya, Gabriel Poesia, Rose E. Wang, and Noah D. Goodman. 2023. Solving Math Word Problems by Combining Language Models With Symbolic Solvers. ArXiv:2304.09102 [cs]. [find](https://scholar.google.com/scholar?q=Joy+He%2DYueya%2C+Gabriel+Poesia%2C+Rose+E%2E+Wang%2C+and+Noah+D%2E+Goodman%2E+2023%2E+Solving+Math+Word+Problems+by+Combining+Language+Models+With+Symbolic+Solvers%2E+ArXiv%3A2304%2E09102+%5Bcs%5D%2E)
11. Aditi Kabra, Jonathan Laurent, Sagar Bharadwaj, Ruben Martins, Stefan Mitsch, and André Platzer. 2025. Can Large Language Models Autoformalize Kinematics? ArXiv:2509.21840 [cs]. — [arXiv:2509.21840](https://arxiv.org/abs/2509.21840) [find](https://scholar.google.com/scholar?q=Aditi+Kabra%2C+Jonathan+Laurent%2C+Sagar+Bharadwaj%2C+Ruben+Martins%2C+Stefan+Mitsch%2C+and+Andr%C3%A9+Platzer%2E+2025%2E+Can+Large+Language+Models+Autoformalize+Kinematics%3F+ArXiv%3A2509%2E21840+%5Bcs%5D%2E+%E2%80%94+%5BarXiv%3A2509%2E21840%5D%28h)
12. Nal Kalchbrenner and Phil Blunsom. 2013. [Recurrent Continuous Translation Models](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-continuous-translation-models/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1700–1709, Seattle, Washington, USA. Association for Computational Linguistics.
13. Shota Kato and Manabu Kano. 2025. VARAT: Variable Annotation Tool for Documents on Manufacturing Processes. Journal of Chemical Engineering of Japan, 58(1):2454461. [find](https://scholar.google.com/scholar?q=Shota+Kato+and+Manabu+Kano%2E+2025%2E+VARAT%3A+Variable+Annotation+Tool+for+Documents+on+Manufacturing+Processes%2E+Journal+of+Chemical+Engineering+of+Japan%2C+58%281%29%3A2454461%2E)
14. Giovanni Yoko Kristianto, Goran Topić, and Akiko Aizawa. 2016. Entity Linking for Mathematical Expressions in Scientific Documents. In Digital Libraries: Knowledge, Information, and Data in an Open Access Society, pages 144–149, Cham. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Giovanni+Yoko+Kristianto%2C+Goran+Topi%C4%87%2C+and+Akiko+Aizawa%2E+2016%2E+Entity+Linking+for+Mathematical+Expressions+in+Scientific+Documents%2E+In+Digital+Libraries%3A+Knowledge%2C+Information%2C+and+Data+in+an+Open+Ac)
15. Ayushi Malik, Pankaj Dadure, and Sahinur Rahman Laskar. 2026. A Review of Mathematical Information Retrieval: Bridging Symbolic Representation and Intelligent Retrieval. Archives of Computational Methods in Engineering, 33(1):577–611. [find](https://scholar.google.com/scholar?q=Ayushi+Malik%2C+Pankaj+Dadure%2C+and+Sahinur+Rahman+Laskar%2E+2026%2E+A+Review+of+Mathematical+Information+Retrieval%3A+Bridging+Symbolic+Representation+and+Intelligent+Retrieval%2E+Archives+of+Computational+Meth)
16. Logan Murphy, Kaiyu Yang, Jialiang Sun, Zhaoyu Li, Anima Anandkumar, and Xujie Si. 2024. Autoformalizing Euclidean Geometry. ArXiv:2405.17216 [cs]. [find](https://scholar.google.com/scholar?q=Logan+Murphy%2C+Kaiyu+Yang%2C+Jialiang+Sun%2C+Zhaoyu+Li%2C+Anima+Anandkumar%2C+and+Xujie+Si%2E+2024%2E+Autoformalizing+Euclidean+Geometry%2E+ArXiv%3A2405%2E17216+%5Bcs%5D%2E)
17. NVIDIA, Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, et al. 2025. NVIDIA Nemotron 3: Efficient and Open Intelligence. ArXiv:2512.20856 [cs]. — [arXiv:2512.20856](https://arxiv.org/abs/2512.20856) [find](https://scholar.google.com/scholar?q=NVIDIA%2C+Aaron+Blakeman%2C+Aaron+Grattafiori%2C+Aarti+Basant%2C+Abhibha+Gupta%2C+Abhinav+Khattar%2C+Adi+Renduchintala%2C+et+al%2E+2025%2E+NVIDIA+Nemotron+3%3A+Efficient+and+Open+Intelligence%2E+ArXiv%3A2512%2E20856+%5Bcs%5D%2E+%E2%80%94+%5Ba)
18. Lukas Panzer and Jan Frederik Schaefer. 2023. AnnoTize: A Flexible Annotation Tool for Documents with Mathematical Formulae. In Proceedings of the 14th MathUI Workshop, Cambridge, UK. [find](https://scholar.google.com/scholar?q=Lukas+Panzer+and+Jan+Frederik+Schaefer%2E+2023%2E+AnnoTize%3A+A+Flexible+Annotation+Tool+for+Documents+with+Mathematical+Formulae%2E+In+Proceedings+of+the+14th+MathUI+Workshop%2C+Cambridge%2C+UK%2E)
19. Ruocheng Shan and Abdou Youssef. 2024. Using large language models to automate annotation and part-of-math tagging of math equations. In Intelligent Computer Mathematics, pages 3–20. Springer Nature Switzerland. [find](https://scholar.google.com/scholar?q=Ruocheng+Shan+and+Abdou+Youssef%2E+2024%2E+Using+large+language+models+to+automate+annotation+and+part%2Dof%2Dmath+tagging+of+math+equations%2E+In+Intelligent+Computer+Mathematics%2C+pages+3%E2%80%9320%2E+Springer+Nature+S)
20. Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, and Bela Gipp. 2023. Neural machine translation for mathematical formulae. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11534–11550. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Felix+Petersen%2C+Moritz+Schubotz%2C+Andre+Greiner%2DPetter%2C+and+Bela+Gipp%2E+2023%2E+Neural+machine+translation+for+mathematical+formulae%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Compu)
21. Mauricio Soroco, Jialin Song, Mengzhou Xia, Kye Emond, Weiran Sun, and Wuyang Chen. 2025. PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs. ArXiv:2502.00963 [cs]. [find](https://scholar.google.com/scholar?q=Mauricio+Soroco%2C+Jialin+Song%2C+Mengzhou+Xia%2C+Kye+Emond%2C+Weiran+Sun%2C+and+Wuyang+Chen%2E+2025%2E+PDE%2DController%3A+LLMs+for+Autoformalization+and+Reasoning+of+PDEs%2E+ArXiv%3A2502%2E00963+%5Bcs%5D%2E)
22. Philipp Scharpf, Ian Mackerracher, Moritz Schubotz, Joeran Beel, Corinna Breitinger, and Bela Gipp. 2019. AnnoMathTeX - a formula identifier annotation recommender system for STEM documents. In Proceedings of the 13th ACM Conference on Recommender Systems, RecSys ’19, pages 532–533, New York, NY, US… [find](https://scholar.google.com/scholar?q=Philipp+Scharpf%2C+Ian+Mackerracher%2C+Moritz+Schubotz%2C+Joeran+Beel%2C+Corinna+Breitinger%2C+and+Bela+Gipp%2E+2019%2E+AnnoMathTeX+%2D+a+formula+identifier+annotation+recommender+system+for+STEM+documents%2E+In+Procee)
23. Björn Schembera, Frank Wübbeling, Hendrik Kleikamp, Burkhard Schmidt, Aurela Shehu, Marco Reidelbach, Christine Biedinger, Jochen Fiedler, Thomas Koprucki, Dorothea Iglezakis, and Dominik Göddeke. 2025. Towards a knowledge graph for models and algorithms in applied mathematics. In Metadata and Seman… [find](https://scholar.google.com/scholar?q=Bj%C3%B6rn+Schembera%2C+Frank+W%C3%BCbbeling%2C+Hendrik+Kleikamp%2C+Burkhard+Schmidt%2C+Aurela+Shehu%2C+Marco+Reidelbach%2C+Christine+Biedinger%2C+Jochen+Fiedler%2C+Thomas+Koprucki%2C+Dorothea+Iglezakis%2C+and+Dominik+G%C3%B6ddeke%2E+202)
24. Felix Schmoll and Tom Wiesing. 2016. KAT: Enabling the Semantification of STEM Documents. In Joint Proceedings of the FM4M, MathUI, and ThEdu Workshops, Doctoral Program, and Work in Progress at the Conference on Intelligent Computer Mathematics 2016 (CICM 2016), volume 1785 of CEUR Workshop Proceed… [find](https://scholar.google.com/scholar?q=Felix+Schmoll+and+Tom+Wiesing%2E+2016%2E+KAT%3A+Enabling+the+Semantification+of+STEM+Documents%2E+In+Joint+Proceedings+of+the+FM4M%2C+MathUI%2C+and+ThEdu+Workshops%2C+Doctoral+Program%2C+and+Work+in+Progress+at+the+C)
25. Moritz Schubotz, André Greiner-Petter, Philipp Scharpf, Norman Meuschke, Howard S. Cohl, and Bela Gipp. 2018. Improving the representation and conversion of mathematical formulae by considering their textual context. In Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, JCDL… [find](https://scholar.google.com/scholar?q=Moritz+Schubotz%2C+Andr%C3%A9+Greiner%2DPetter%2C+Philipp+Scharpf%2C+Norman+Meuschke%2C+Howard+S%2E+Cohl%2C+and+Bela+Gipp%2E+2018%2E+Improving+the+representation+and+conversion+of+mathematical+formulae+by+considering+their+)
26. Moritz Schubotz, Alexey Grigorev, Marcus Leich, Howard S. Cohl, Norman Meuschke, Bela Gipp, Abdou S. Youssef, and Volker Markl. 2016. Semantification of identifiers in mathematics for better math information retrieval. In Proceedings of the 39th International ACM SIGIR conference on Research and Dev… [find](https://scholar.google.com/scholar?q=Moritz+Schubotz%2C+Alexey+Grigorev%2C+Marcus+Leich%2C+Howard+S%2E+Cohl%2C+Norman+Meuschke%2C+Bela+Gipp%2C+Abdou+S%2E+Youssef%2C+and+Volker+Markl%2E+2016%2E+Semantification+of+identifiers+in+mathematics+for+better+math+info)
27. Zhixing Tan, Shuo Wang, Zonghan Yang, Gang Chen, Xuancheng Huang, Maosong Sun, and Yang Liu. 2020. Neural machine translation: A review of methods, resources, and tools. AI Open, 1:5–21. [find](https://scholar.google.com/scholar?q=Zhixing+Tan%2C+Shuo+Wang%2C+Zonghan+Yang%2C+Gang+Chen%2C+Xuancheng+Huang%2C+Maosong+Sun%2C+and+Yang+Liu%2E+2020%2E+Neural+machine+translation%3A+A+review+of+methods%2C+resources%2C+and+tools%2E+AI+Open%2C+1%3A5%E2%80%9321%2E)
28. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, et al. 2025. Gemma 3 Technical Report. ArXiv:2503.19786 [cs]. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+et+al%2E+2025%2E+Gemma+3+Technical+Report%2E+ArXiv%3A2503%2E19786+%5Bcs%5D%2E)
29. Ke Weng, Lun Du, Sirui Li, Wangyue Lu, Haozhe Sun, Hengyu Liu, and Tiancheng Zhang. 2025. Autoformalization in the Era of [Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). ArXiv:2505.23486 [cs].
30. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, et al. 2025. [Qwen3 Technical Report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). ArXiv:2505.09388 [cs].
31. Abdou Youssef. 2017. Part-of-Math Tagging and Applications. In Intelligent Computer Mathematics, volume 10383 of Lecture Notes in Computer Science, pages 356–374. Springer International Publishing, Cham. [find](https://scholar.google.com/scholar?q=Abdou+Youssef%2E+2017%2E+Part%2Dof%2DMath+Tagging+and+Applications%2E+In+Intelligent+Computer+Mathematics%2C+volume+10383+of+Lecture+Notes+in+Computer+Science%2C+pages+356%E2%80%93374%2E+Springer+International+Publishing%2C+Ch)
32. Lan Zhang, Marco Valentino, and Andre Freitas. 2025. Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 1720–1738. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lan+Zhang%2C+Marco+Valentino%2C+and+Andre+Freitas%2E+2025%2E+Autoformalization+in+the+Wild%3A+Assessing+LLMs+on+Real%2DWorld+Mathematical+Definitions%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in)
33. Kunhao Zheng, Jesse Michael Han, and Stanislas Polu. 2022. [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://md.research.elamur.ai/free/en/papers/zheng-2021-minif2f-cross-system-benchmark-formal/). ArXiv:2109.00110 [cs].
34. O.C. Zienkiewicz, R.L. Taylor, and S. Govindjee. 2024. The Finite Element Method: Its Basis and Fundamentals, 8th edition. Butterworth-Heinemann. [find](https://scholar.google.com/scholar?q=O%2EC%2E+Zienkiewicz%2C+R%2EL%2E+Taylor%2C+and+S%2E+Govindjee%2E+2024%2E+The+Finite+Element+Method%3A+Its+Basis+and+Fundamentals%2C+8th+edition%2E+Butterworth%2DHeinemann%2E)
35. Jiaru Zou, Qing Wang, Pratyush Thakur, and Nickvash Kani. 2025. STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing. ArXiv:2411.00387 [cs]. [find](https://scholar.google.com/scholar?q=Jiaru+Zou%2C+Qing+Wang%2C+Pratyush+Thakur%2C+and+Nickvash+Kani%2E+2025%2E+STEM%2DPOM%3A+Evaluating+Language+Models+Math%2DSymbol+Reasoning+in+Document+Parsing%2E+ArXiv%3A2411%2E00387+%5Bcs%5D%2E)

*Updated 1 November 2026*