GSM8K

8.5k grade-school math word problems requiring multi-step arithmetic reasoning.

Papers using GSM8K (127)

Gsm-symbolic: Understanding The Limitations Of Mathematical Reasoning In Large Language Models2024 · 499 citesHRM-Text: Efficient Pretraining Beyond Scaling2026Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025 · 26 citesRethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry2026On the Limits of Layer Pruning for Generative Reasoning in Large Language Models2026PARTREP: Learning What to Repeat for Decoder-only LLMs2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM2026Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing2026More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges2026Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation2026Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization2026Fora: From Weight-Space to Function-Space Protection in Capability-Preserving Fine-Tuning2026Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning2026Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning2026REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak2026How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws2026The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic2026Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding2025 · 2 citesThe Price of Format: Diversity Collapse in LLMs2025 · 2 citesPruning via Causal Attribution Preserves Reasoning Performance in Large Language Models2026EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction2026When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation2026Exploring LLM Reasoning Through Controlled Prompt Variations2025 · 1 citesKV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling2026Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning2026Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers2026Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection2026Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference2026EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs2026QEIL v2: Heterogeneous Computing for Edge Intelligence via Roofline-Derived Pareto-Optimal Energy Modeling and Multi-Objective Orchestration2026Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs2026Training Language Models via Neural Cellular Automata2026S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models2026Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling2026Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning2026LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models2026Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting2026Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs2026The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models2026Value-Based Pre-Training with Downstream Feedback2026Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns2026Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs2026Strategic Over-Parameterization for Generalizable Low-Rank Adaptation2026Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA2026Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima2026Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities2026AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency2026DMax: Aggressive Parallel Decoding for dLLMs2026Residual Stream Analysis of Overfitting And Structural Disruptions2026SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing2026TAPS: Task Aware Proposal Distributions for Speculative Sampling2026Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation2026Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval2026ROAST: Rollout-based On-distribution Activation Steering Technique2026FIT to Forget: Robust Continual Unlearning for Large Language Models2026Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning2025Group-Aware Reinforcement Learning for Output Diversity in Large Language Models2025Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems2025Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance2025Prototype-Based Dynamic Steering for Large Language Models2025Dr.LLM: Dynamic Layer Routing in LLMs2025A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space2025Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning2025From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs2025LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures2025Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs2025CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks2025P3: Prompts Promote Prompting2025Text-to-LoRA: Instant Transformer Adaption2025Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search2025Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty2025FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving2025Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution2025AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection2025Thinkless: LLM Learns When to Think2025EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning2025Learning a Continue-Thinking Token for Enhanced Test-Time Scaling2025Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute2025Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future2025Aryabhata: An exam-focused language model for JEE Math2025Inpainting-Guided Policy Optimization for Diffusion Large Language Models2025Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution2025Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance2025Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts2025LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding2025Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks2025Learning to Insert [PAUSE] Tokens for Better Reasoning2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference2025Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges2025SIFT: Grounding LLM Reasoning in Contexts via Stickers2025Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?2025Entropy-Based Adaptive Weighting for Self-Training2025Sample, Don't Search: Rethinking Test-Time Alignment for Language Models2025Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models2025CommVQ: Commutative Vector Quantization for KV Cache Compression2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing2025dParallel: Learnable Parallel Decoding for dLLMs2025QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs2025AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection2025Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning2025Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst2025Dual Decomposition of Weights and Singular Value Low Rank Adaptation2025Efficient Data Selection at Scale via Influence Distillation2025Adaptive Rectification Sampling for Test-Time Compute Scaling2025Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models2025Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models2025Leveraging Uncertainty Estimation for Efficient LLM Routing2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs2025Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?2025Self-Training Elicits Concise Reasoning in Large Language Models2025Evolutionary Pre-Prompt Optimization for Mathematical Reasoning2024DIVE: Diversified Iterative Self-Improvement2025Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models2024Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation2024 · 4 citesThink Beyond Size: Adaptive Prompting for More Effective Reasoning2024 · 1 citesLanguage Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding2024 · 1 citesUnderstanding Chain-of-Thought in LLMs through Information Theory2024 · 1 citesUnlocking Structured Thinking in Language Models with Cognitive Prompting2024Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation2024Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment2024Reasoning Robustness of LLMs to Adversarial Typographical Errors2024Learning to Reason via Self-Iterative Process Feedback for Small Language Models2024GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers2024Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions2024LLM2: Let Large Language Models Harness System 2 Reasoning2024CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning2024