| Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation | Sep 5, 2024 | GSM8K | —Unverified | 0 | 0 |
| Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation | May 29, 2025 | GSM8KMath | —Unverified | 0 | 0 |
| STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning | Sep 10, 2024 | GSM8KMixture-of-Experts | —Unverified | 0 | 0 |
| Subtle Errors Matter: Preference Learning via Error-injected Self-editing | Oct 9, 2024 | GSM8KMath | —Unverified | 0 | 0 |
| Building Math Agents with Multi-Turn Iterative Preference Learning | Sep 4, 2024 | GSM8KMath | —Unverified | 0 | 0 |
| BrainTransformers: SNN-LLM | Oct 3, 2024 | ARCGSM8K | —Unverified | 0 | 0 |
| Supervised Optimism Correction: Be Confident When LLMs Are Sure | Apr 10, 2025 | GSM8KMath | —Unverified | 0 | 0 |
| Supervisory Prompt Training | Mar 26, 2024 | GSM8KSentence | —Unverified | 0 | 0 |
| Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency | Apr 4, 2025 | BenchmarkingGSM8K | —Unverified | 0 | 0 |
| SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning | Feb 20, 2024 | Arithmetic ReasoningGSM8K | —Unverified | 0 | 0 |
