RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
arXiv:2609.00062v1 Announce Type: new Abstract: Data contamination undermines the reliable evaluation of large language models (LLMs) on mathematical problem solving. While rewriting-based evaluation mitigates memorization, existing methods lack guarantees of problem validity and answer correctness. We propose Proof-Verified Benchmark Rewriting (RePro), the first framework to integrate Lean-oriented neural automated theorem provers (ATPs) into benchmark rewriting, which rewrites problems and regenerates answers with correctness ensured by Lean-verified proofs. Experiments on GSM8K and MATH show that RePro's retained rewritten instances achieve 100% well-definedness, feasibility, and answer correctness, while existing methods still produce invalid or incorrect instances. Moreover, several models exhibit accuracy drops on proof-verified rewritten benchmarks, suggesting that their performance is sensitive to surface-level and structural variations and may partly reflect memorization effects. Our source code and data are available at https://github.com/AI4Engi/RePro.
-->
[Submitted on 30 Aug 2026]
Title:RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
View a PDF of the paper titled RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving, by Xiyuan Zhou and 8 other authors
View PDF HTML (experimental)
Abstract:Data contamination undermines the reliable evaluation of large language models (LLMs) on mathematical problem solving. While rewriting-based evaluation mitigates memorization, existing methods lack guarantees of problem validity and answer correctness. We propose Proof-Verified Benchmark Rewriting (RePro), the first framework to integrate Lean-oriented neural automated theorem provers (ATPs) into benchmark rewriting, which rewrites problems and regenerates answers with correctness ensured by Lean-verified proofs. Experiments on GSM8K and MATH show that RePro's retained rewritten instances achieve 100% well-definedness, feasibility, and answer correctness, while existing methods still produce invalid or incorrect instances. Moreover, several models exhibit accuracy drops on proof-verified rewritten benchmarks, suggesting that their performance is sensitive to surface-level and structural variations and may partly reflect memorization effects. Our source code and data are available at this https URL.
Comments: Accepted to the EMNLP 2026 Main Conference
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2609.00062 [cs.CL]
(or arXiv:2609.00062v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.00062
arXiv-issued DOI via DataCite
Submission history
From: Xiyuan Zhou [view email] [v1] Sun, 30 Aug 2026 14:23:48 UTC (1,870 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving, by Xiyuan Zhou and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-09
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)