Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 77 tok/s
Gemini 2.5 Pro 54 tok/s Pro
GPT-5 Medium 29 tok/s Pro
GPT-5 High 26 tok/s Pro
GPT-4o 103 tok/s Pro
Kimi K2 175 tok/s Pro
GPT OSS 120B 454 tok/s Pro
Claude Sonnet 4.5 38 tok/s Pro
2000 character limit reached

Improving the Diproche CNL through Autoformalization via Large Language Models (2303.17513v3)

Published 12 Mar 2023 in cs.CL and cs.LO

Abstract: The Diproche system is an automated proof checker for texts written in a controlled fragment of German, designed for didactical applications in classes introducing students to proofs for the first time. The first version of the system used a controlled natural language for which a Prolog formalization routine was written. In this paper, we explore the possibility of prompting LLMs for autoformalization in the context of Diproche, with encouraging first results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (12)
  1. ArXiv, 10.48550/arXiv.2302.12433. arXiv:https://arxiv.org/abs/abs/2302.12433.
  2. Christoph Benzmüller, Florian Rabe & Geoff Sutcliffe (2008): THF0 – The Core of the TPTP Language for Higher-Order Logic. In A. Armando, P. Baumgartner & G. Dowek, editors: Automated Reasoning. IJCAR 2008, 5195, pp. 491–506, 10.1007/978-3-540-71070-7_41.
  3. Merlin Carl (2020): Number Theory and Axiomatic Geometry in the Diproche System. Electronic Proceedings in Theoretical Computer Science 328, pp. 56–78, 10.4204/EPTCS.328.4.
  4. Merlin Carl & Regula Krapf (2020): Diproche - ein automatisierter Tutor für den Einstieg ins Beweisen. In: Digitale Kompetenzen und Curriculare Konsequenzen, pp. 43–56.
  5. Merlin Carl, Hinrich Lorenzen & MIchael Schmitz (2022): Natural Language Proof Checking in Introduction to Proof Classes – First Experiences with Diproche. Electronic Proceedings in Theoretical Computer Science 354, pp. 59–70, 10.4204/EPTCS.354.5.
  6. Lingjiao Chen, Matei Zaharia & James Y. Zou (2023): How is ChatGPT’s behavior changing over time? ArXiv abs/2307.09009, 10.48550/arXiv.2307.09009. Available at https://api.semanticscholar.org/CorpusID:259951081.
  7. Marcos Cramer (2013): Proof-checking mathematical texts in controlled natural language. Ph.D. thesis, Rheinische Friedrich-Wilhelms-Universität Bonn”.
  8. In: Controlled Natural Language. CNL 2009, 5972, pp. 170–186, 10.1007/978-3-642-14418-9_11.
  9. Mohan Ganesalingam (2013): The language of mathematics. Springer Berlin Heidelberg, 10.1007/978-3-642-37012-0.
  10. Peter Koepke & Bernhard Schröder (2003): ProofML - eine Annotationssprache für natürliche Beweise. LDV Forum 18, pp. 428–441, 10.21248/jlcl.18.2003.48. Available at https://api.semanticscholar.org/CorpusID:30895733.
  11. In: CPP 2020: Proceedings of the 9th ACM SIGPLAN International Conference on Certified Programs and Proofs, pp. 85–98, 10.1145/3372885.3373827.
  12. In: 36th Conference on Neural Information Processing Systems (NeurIPS), 10.48550/arXiv.2205.12615.
Citations (1)

Summary

We haven't generated a summary for this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Authors (1)

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 post and received 1 like.