SOTAVerified

Math

Papers

Showing 326350 of 1596 papers

TitleStatusHype
Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language ModelsCode1
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic ConsistencyCode1
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of HeuristicsCode1
Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesCode1
Non-myopic Generation of Language Models for Reasoning and PlanningCode1
LoRA Soups: Merging LoRAs for Practical Skill Composition TasksCode1
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical ReasoningCode1
HARDMath: A Benchmark Dataset for Challenging Problems in Applied MathematicsCode1
The Geometry of Concepts: Sparse Autoencoder Feature StructureCode1
DataEnvGym: Data Generation Agents in Teacher Environments with Student FeedbackCode1
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsCode1
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree SearchCode1
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningCode1
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for ReasoningCode1
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
Explaining Datasets in Words: Statistical Models with Natural Language ParametersCode1
Sirius: Contextual Sparsity with Correction for Efficient LLMsCode1
MultiMath: Bridging Visual and Mathematical Reasoning for Large Language ModelsCode1
What makes math problems hard for reinforcement learning: a case studyCode1
SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language ModelsCode1
Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical ReasoningCode1
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
Mathfish: Evaluating Language Model Math Reasoning via Grounding in Educational CurriculaCode1
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty AgentsCode1
Boosting Large Language Models with Socratic Method for Conversational Mathematics TeachingCode1
Show:102550
← PrevPage 14 of 64Next →

No leaderboard results yet.