arXiv AI
Beyond the Answer Key: Robustness Evaluation of Large Language Models for Step-Level Mathematical Verification
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jul 13
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics remain poorly understood. Existing benchmarks, however, fall short in both scope and evaluation granularity: they provide limited disciplinary coverage and often rely on final-answer correctness or coarse judgments, leaving the validity of the reasoning process inadequately assessed.
arXiv Machine Learning
Jun 24
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
arXiv:2603. 15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification.
arXiv Computation and Language
Aug 21
Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning
arXiv:2608. 19009v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors.
arXiv AI
Aug 18
Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
arXiv:2603. 18334v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly assist secure software development, their ability to meet the rigorous demands of Rust program verification remains unclear.
arXiv AI
Aug 28
FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
FaithSieve is a Lean‑assisted framework that fine‑grains natural‑language mathematical proofs into local reasoning units, extracts typed proof obligations, and verifies them with formal evidence gated by semantic alignment. It introduces two expert‑verified datasets—ProofLoc‑Olympiad and ProofLoc‑University—to benchmark first‑error localization. On these benchmarks, FaithSieve outperforms direct‑judging baselines, achieving 81.43% and 84.5% exact first‑error accuracy respectively.
arXiv Machine Learning
Sep 10
Robustness of LLM-Generated SystemVerilog Assertions to Semantics-Preserving RTL Transformations
The paper evaluates how robust large language models are at generating SystemVerilog Assertions (SVA) when the underlying RTL code undergoes semantics‑preserving transformations such as operand reordering, identifier renaming, and redundant parenthesization. Using a curated dataset and two open‑source models (Qwen2.5‑Coder‑7B and DeepSeek‑Coder‑V2‑Lite), the authors find that 9.7%–27.0% of behaviors that were correct on the original RTL become incorrect after transformation, revealing significant instability that aggregate accuracy metrics can hide.