mathematical reasoning

Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems ICLR 2025 PORT: Preference Optimization on Reasoning Traces NAACL 2025 Predicate-Guided Generation for Mathematical Reasoning EMNLP 2025 Preference Optimization for Reasoning with Pseudo Feedback ICLR 2025 Probability-Consistent Preference Optimization for Enhanced LLM Reasoning ACL 2025 Process-based Self-Rewarding Language Models ACL 2025 ProcessBench: Identifying Process Errors in Mathematical Reasoning ACL 2025 PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models ACL 2025 Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs ICML 2025 QDTSynth: Quality-Driven Formal Theorem Synthesis for Enhancing Proving Performance of LLMs ACL 2025 RaDeR: Reasoning-aware Dense Retrieval Models EMNLP 2025 Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach ICLR 2025 Retrieval-Augmented Language Models are Mimetic Theorem Provers EMNLP 2025 Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning ACL 2025 Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot EMNLP 2025 Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation ACL 2025 RMath: A Logic Reasoning-Focused Datasets Toward Mathematical Multistep Reasoning Tasks AAAI 2025 RoMath: A Mathematical Reasoning Benchmark in Romanian EMNLP 2025 R-PRM: Reasoning-Driven Process Reward Modeling EMNLP 2025 S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners AAAI 2025 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification ACL 2025 SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning EMNLP 2025 SBSC: Step-by-Step Coding for Improving Mathematical Olympiad Performance ICLR 2025 Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning ICLR 2025 SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation ACL 2025