SOTAVerified

GSM8K

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 439 papers

TitleStatusHype
Enhancing Knowledge Distillation for LLMs with Response-Priming PromptingCode0
Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree—0
SepLLM: Accelerate Large Language Models by Compressing One Segment into One SeparatorCode4
Entropy-Regularized Process Reward ModelCode1
GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt OptimizersCode1
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesCode1
A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions—0
SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs—0
Learning to Reason via Self-Iterative Process Feedback for Small Language Models—0
ProcessBench: Identifying Process Errors in Mathematical ReasoningCode2
Evolutionary Pre-Prompt Optimization for Mathematical Reasoning—0
How to Correctly do Semantic Backpropagation on Language-based Agentic SystemsCode2
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning—0
MALT: Improving Reasoning with Multi-Agent LLM Training—0
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityCode1
Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference—0
Predicting Emergent Capabilities by Finetuning—0
Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures—0
Preference Optimization for Reasoning with Pseudo FeedbackCode2
Patience Is The Key to Large Language Model Reasoning—0
Adaptive Decoding via Latent Preference Optimization—0
Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models—0
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?Code1
UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding ThoughtsCode1
Quasi-random Multi-Sample Inference for Large Language Models—0
Reasoning Robustness of LLMs to Adversarial Typographical Errors—0
Kwai-STaR: Transform LLMs into State-Transition Reasoners—0
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-RewardingCode2
Self-Consistency Preference Optimization—0
Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models—0
Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation—0
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA OptimizationCode1
ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning—0
Scaling up Masked Diffusion Models on TextCode3
Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment—0
Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesCode1
Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation—0
SMART: Self-learning Meta-strategy Agent for Reasoning TasksCode0
On Designing Effective RL Reward at Training Time for LLM Reasoning—0
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling—0
SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented GenerationCode0
Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math ReasoningCode0
MIND: Math Informed syNthetic Dialogues for Pretraining LLMs—0
One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning TasksCode0
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning PerspectiveCode0
COrAL: Order-Agnostic Language Modeling for Efficient Iterative RefinementCode0
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function OptimizationCode2
Nudging: Inference-time Alignment of LLMs via Guided Decoding—0
SuperCorrect: Supervising and Correcting Language Models with Error-Driven InsightsCode4
Towards Multilingual LLM Evaluation for European Languages—0
Show:102550
← PrevPage 4 of 9Next →

Benchmark Results

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