ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2605.28365· 19 results

cs.LGcs.AIRecentMay 27, 2026

FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks

Nishal Thomas, Noel Thomas

The paper introduces FormInv, a measurement protocol that reveals significant semantic inconsistencies in existing mathematical reasoning benchmarks, showing that standard accuracy metrics fail to cap…

View →
cs.AIcs.CLcs.LGRecentMay 30, 2026

AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Reasoning

Alessio Bruno

AXIOM is a trust-first neuro-symbolic execution architecture that ensures verifiable mathematical reasoning by strictly separating language model interpretation from deterministic computation, achievi…

View →
cs.CLcs.AIcs.LGRecentJun 1, 2026

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

Atoosa Chegini, Soheil Feizi

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

View →
cs.CRcs.AIRecentJun 2, 2026

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

Malia Barker, Bishal Lakha, Edoardo Serra, Francesco Gullo

The paper introduces an automatic numeric-remapping attack to test the robustness of LLMs on arithmetic word problems, finding that LLMs remain sensitive to small numeric changes in datasets like GSM8…

View →
cs.AIRecentMay 28, 2026

Formalizing Mathematics at Scale

Ahmad Rammal, Niket Patel, Fabian Gloeckle, Amaury Hayat +4 more

The paper introduces AutoformBot, a multi-agent system that successfully autoformalizes a large corpus of open-access graduate-level mathematics textbooks into a verified library in Lean 4, demonstrat…

View →
cs.LOcs.AIcs.CRRecentApr 1, 2026

Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving

Devakh Rashie, Veda Rashi

The paper introduces the Lean-Agent Protocol, a formal verification platform that uses Lean 4 theorem proving to ensure agentic AI actions in finance are mathematically compliant with complex regulati…

View →
cs.AIcs.LGRecentJun 1, 2026

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov +2 more

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

View →
cs.CLcs.AIRecentJun 2, 2026

Quantifying Faithful Confidence Expression in Large Reasoning Models

Areeb Gani, Asal Meskin, Gabrielle Kaili-May Liu, Arman Cohan

The paper introduces a novel framework to quantify faithful confidence expression (FC) in Large Reasoning Models (LRMs), finding that FC remains a significant and challenging reliability target for th…

View →
cs.CRcs.AIcs.CLRecentMay 5, 2026

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis

Haoyu Zhang, Mohammad Zandsalimy, Shanu Sushmita

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

View →
cs.SEcs.AIRecentMay 31, 2026

FVSpec: Real-World Property-Based Tests as Lean Challenges

Quinn Dougherty, Max von Hippel, Hazel Shackleton, Mike Dodds

The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…

View →
cs.AIcs.CLcs.LORecentMay 27, 2026

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability

Leizhen Zhang, Shuhan Chen, Sheng Chen

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

View →
cs.AIcs.CRRecentMar 26, 2026

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

Xunguang Wang, Yuguang Zhou, Qingyue Wang, Zongjie Li +4 more

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

View →
cs.CLcs.AIRecentMay 27, 2026

Skill-Conditioned Gated Self-Distillation for LLM Reasoning

Jiazhen Huang, Xiao Chen, Xiao Luo, Yong Dai +2 more

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on m…

View →
cs.SEcs.AIRecentMay 28, 2026

Inferring Code Correctness from Specification

Tambon Florian, Papadakis Mike

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

View →
cs.LGcs.AIcs.CLRecentMay 28, 2026

Reasoning with Sampling: Cutting at Decision Points

Felix Zhou, Anay Mehrotra, Quanquan C. Liu

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…

View →
cs.AIcs.CLcs.LGRecentMay 28, 2026

Conformal Certification of Reasoning Trace Prefixes

Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen, Guha Balakrishnan

The paper introduces CROP, a novel conformal procedure that provides rigorous statistical guarantees for certifying the longest safe prefix of a language model's reasoning trace, allowing for targeted…

View →
cs.LOcs.CLcs.CRRecentMay 13, 2026

Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture

George Koomullil

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

View →
cs.AIRecentMay 28, 2026

TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation

Yundong Kim, Heyoung Yang

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

View →
cs.CRcs.LGRecentMar 19, 2026

Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference

Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro +3 more

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

View →