Objects Without Morphisms: What LLMs for Mathematics Do Not Represent
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Abstraction boundaries and spec driven development in pure mathematics
- FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
- Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs
- Measuring Mathematical Problem Solving With the MATH Dataset
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- HyperTree Proof Search for Neural Theorem Proving
- CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists
- Solving Quantitative Reasoning Problems with Language Models
- Let's Verify Step by Step
- GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
- The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- NaturalProofs: Mathematical Theorem Proving in Natural Language
- Mathesis: Towards Formal Theorem Proving from Natural Languages
- Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks