Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Thomas, Nishal, Thomas, Noel
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale
par: Thomas, Noel
Publié: (2026)

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
par: Noël, Valentin
Publié: (2026)

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
par: Yu, Zhouliang, et autres
Publié: (2025)

Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
par: Herbst, Daniel, et autres
Publié: (2025)

I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models
par: Camposampiero, Giacomo, et autres
Publié: (2025)

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
par: Hao, Yuren, et autres
Publié: (2025)

xInv: Explainable Optimization of Inverse Problems
par: Memery, Sean, et autres
Publié: (2025)

InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
par: Huang, Chenyu, et autres
Publié: (2026)

VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks
par: Yao, Jian, et autres
Publié: (2025)

DABstep: Data Agent Benchmark for Multi-step Reasoning
par: Egg, Alex, et autres
Publié: (2025)

Mathematics and Coding are Universal AI Benchmarks
par: Chojecki, Przemyslaw
Publié: (2025)

Continuous Invariance Learning
par: Lin, Yong, et autres
Publié: (2023)

HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
par: Fan, Jingxuan, et autres
Publié: (2024)

Cross-Model Semantics in Representation Learning
par: Nikooroo, Saleh, et autres
Publié: (2025)

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning
par: Liang, Sirui, et autres
Publié: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
par: Li, Zhen, et autres
Publié: (2025)

Learning with Exact Invariances in Polynomial Time
par: Soleymani, Ashkan, et autres
Publié: (2025)

DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs
par: Zhang, Yuanhe, et autres
Publié: (2025)

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
par: Cinquin, Tristan, et autres
Publié: (2025)

MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning
par: Lin, Yunze
Publié: (2025)

MaRVL-QA: A Benchmark for Mathematical Reasoning over Visual Landscapes
par: Pande, Nilay, et autres
Publié: (2025)

PuzzleJAX: A Benchmark for Reasoning and Learning
par: Earle, Sam, et autres
Publié: (2025)

PUZZLES: A Benchmark for Neural Algorithmic Reasoning
par: Estermann, Benjamin, et autres
Publié: (2024)

From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning
par: Yoa, Seungdong, et autres
Publié: (2026)

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
par: Alshammari, Shaden, et autres
Publié: (2026)

InvDesFlow-AL: active learning-based workflow for inverse design of functional materials
par: Han, Xiao-Qi, et autres
Publié: (2025)

Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
par: Peng, Ruiying, et autres
Publié: (2026)

Learning Action-based Representations Using Invariance
par: Rudolph, Max, et autres
Publié: (2024)

Handling Distribution Shifts on Graphs: An Invariance Perspective
par: Wu, Qitian, et autres
Publié: (2022)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
par: Mirzadeh, Iman, et autres
Publié: (2024)

CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
par: Zan, Lei, et autres
Publié: (2025)

Advanced Weakly-Supervised Formula Exploration for Neuro-Symbolic Mathematical Reasoning
par: Wu, Yuxuan, et autres
Publié: (2025)

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
par: Lin, Yen-Ting, et autres
Publié: (2025)

Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning
par: Pawar, Pranav, et autres
Publié: (2025)

HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class
par: Roggeveen, James V., et autres
Publié: (2025)

Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion
par: Gao, Ang, et autres
Publié: (2026)

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis
par: Ondras, Jan, et autres
Publié: (2025)

CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning
par: Gao, Zijun, et autres
Publié: (2025)

Operator-Guided Invariance Learning for Continuous Reinforcement Learning
par: Zhang, Zuyuan, et autres
Publié: (2026)

Representation Invariance and Allocation: When Subgroup Balance Matters
par: Alloula, Anissa, et autres
Publié: (2025)