SOTAVerified

GSM8K

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 439 papers

TitleStatusHype
Multiple-Choice Questions are Efficient and Robust LLM EvaluatorsCode1
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human AnnotationsCode1
MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model EvaluationCode1
Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word ProblemsCode1
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning ProofsCode1
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-ContrastCode1
AskIt: Unified Programming Interface for Programming with Large Language ModelsCode1
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language ModelsCode1
DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical ReasoningCode1
Entropy-Regularized Process Reward ModelCode1
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with AutoformalizationCode1
Markovian Transformers for Informative Language ModelingCode1
SMART: Self-Aware Agent for Tool Overuse MitigationCode1
Solving Math Word Problems by Combining Language Models With Symbolic SolversCode1
Self-Training Elicits Concise Reasoning in Large Language ModelsCode1
Self-Polish: Enhance Reasoning in Large Language Models via Problem RefinementCode1
OVM, Outcome-supervised Value Models for Planning in Mathematical ReasoningCode1
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationCode1
GRACE: Discriminator-Guided Chain-of-Thought ReasoningCode1
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and ObservationsCode1
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA OptimizationCode1
Self-Consistency Improves Chain of Thought Reasoning in Language ModelsCode1
SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language ModelsCode1
Boosted Prompt Ensembles for Large Language ModelsCode1
Design of Chain-of-Thought in Math Problem SolvingCode1
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesCode1
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator AgentCode1
Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context LearningCode1
Rewriting Pre-Training Data Boosts LLM Performance in Math and CodeCode1
Learning From Mistakes Makes LLM Better ReasonerCode1
Learning Goal-Conditioned Representations for Language Reward ModelsCode1
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model MergingCode1
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language ModelsCode1
Large Language Models as OptimizersCode1
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsCode1
GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt OptimizersCode1
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityCode1
Large Language Models are Contrastive ReasonersCode1
Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context LearningCode1
Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive PrinciplesCode1
Large (Vision) Language Models are Unsupervised In-Context LearnersCode1
Matrix Information Theory for Self-Supervised LearningCode1
Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesCode1
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language ModelsCode1
IRanker: Towards Ranking Foundation ModelCode1
Language Models as Science TutorsCode1
FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle SolvingCode1
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based SamplingCode1
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt TemplatesCode1
Show:102550
← PrevPage 3 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1XolverAccuracy98.1—Unverified
2Orange-mini0-shot MRR98—Unverified