| Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries | Dec 12, 2024 | 4kGSM8K | CodeCode Available | 1 | 5 |
| Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions | May 28, 2022 | Arithmetic ReasoningEfficient Exploration | CodeCode Available | 1 | 5 |
| Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent | Sep 17, 2024 | GSM8KQuestion Answering | CodeCode Available | 1 | 5 |
| Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning | May 18, 2025 | GSM8KIn-Context Learning | CodeCode Available | 1 | 5 |
| Rewriting Pre-Training Data Boosts LLM Performance in Math and Code | May 5, 2025 | Code GenerationGSM8K | CodeCode Available | 1 | 5 |
| Learning From Mistakes Makes LLM Better Reasoner | Oct 31, 2023 | GSM8KMath | CodeCode Available | 1 | 5 |
| Learning Goal-Conditioned Representations for Language Reward Models | Jul 18, 2024 | GSM8KMath | CodeCode Available | 1 | 5 |
| SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging | Mar 21, 2025 | GSM8KSafety Alignment | CodeCode Available | 1 | 5 |
| Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models | May 29, 2025 | 2k4k | CodeCode Available | 1 | 5 |
| Large Language Models as Optimizers | Sep 7, 2023 | GSM8K | CodeCode Available | 1 | 5 |
| GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models | Oct 7, 2024 | GSM8KLogical Reasoning | CodeCode Available | 1 | 5 |
| GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers | Dec 12, 2024 | GSM8KPrompt Engineering | CodeCode Available | 1 | 5 |
| Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability | Nov 29, 2024 | GSM8KMath | CodeCode Available | 1 | 5 |
| Large Language Models are Contrastive Reasoners | Mar 13, 2024 | GSM8K | CodeCode Available | 1 | 5 |
| Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning | Jan 27, 2023 | Few-Shot LearningGSM8K | CodeCode Available | 1 | 5 |
| Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles | Jun 18, 2024 | Arithmetic ReasoningCode Generation | CodeCode Available | 1 | 5 |
| Large (Vision) Language Models are Unsupervised In-Context Learners | Apr 3, 2025 | GSM8KIn-Context Learning | CodeCode Available | 1 | 5 |
| Matrix Information Theory for Self-Supervised Learning | May 27, 2023 | Contrastive LearningGSM8K | CodeCode Available | 1 | 5 |
| Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes | Oct 22, 2024 | GSM8KLanguage Modeling | CodeCode Available | 1 | 5 |
| Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models | Nov 10, 2023 | GSM8KMemorization | CodeCode Available | 1 | 5 |
| IRanker: Towards Ranking Foundation Model | Jun 25, 2025 | GSM8Kmodel | CodeCode Available | 1 | 5 |
| Language Models as Science Tutors | Feb 16, 2024 | GSM8KMath | CodeCode Available | 1 | 5 |
| FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving | Feb 27, 2025 | GSM8KMath | CodeCode Available | 1 | 5 |
| DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling | Jun 17, 2024 | GSM8KMath | CodeCode Available | 1 | 5 |
| Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates | Feb 28, 2024 | GSM8KSafety Alignment | CodeCode Available | 1 | 5 |
