| Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning | Dec 14, 2023 | Arithmetic ReasoningFew-Shot Learning | —Unverified | 0 |
| Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations | Dec 14, 2023 | Arithmetic ReasoningGSM8K | CodeCode Available | 1 |
| Training Chain-of-Thought via Latent-Variable Inference | Nov 28, 2023 | GSM8K | —Unverified | 0 |
| AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations | Nov 22, 2023 | Common Sense ReasoningGSM8K | CodeCode Available | 0 |
| Meta Prompting for AI Systems | Nov 20, 2023 | Data InteractionGSM8K | CodeCode Available | 2 |
| Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization | Nov 17, 2023 | ARCGSM8K | CodeCode Available | 1 |
| OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning | Nov 16, 2023 | Arithmetic ReasoningGSM8K | CodeCode Available | 1 |
| Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs | Nov 16, 2023 | Arithmetic ReasoningGSM8K | CodeCode Available | 1 |
| First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning | Nov 14, 2023 | GSM8KMath | —Unverified | 0 |
| The ART of LLM Refinement: Ask, Refine, and Trust | Nov 14, 2023 | Arithmetic ReasoningGSM8K | —Unverified | 0 |
