| Progressive-Hint Prompting Improves Reasoning in Large Language Models | Apr 19, 2023 | Arithmetic ReasoningGSM8K | CodeCode Available | 2 |
| Solving Math Word Problems by Combining Language Models With Symbolic Solvers | Apr 16, 2023 | GSM8KLanguage Modeling | CodeCode Available | 1 |
| Boosted Prompt Ensembles for Large Language Models | Apr 12, 2023 | GSM8KLanguage Modeling | CodeCode Available | 1 |
| 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 |
| Teaching Small Language Models to Reason | Dec 16, 2022 | GSM8KKnowledge Distillation | —Unverified | 0 |
| Distilling Reasoning Capabilities into Smaller Language Models | Dec 1, 2022 | GSM8KKnowledge Distillation | CodeCode Available | 0 |
| Explicit Knowledge Transfer for Weakly-Supervised Code Generation | Nov 30, 2022 | Code GenerationFew-Shot Learning | —Unverified | 0 |
| Solving math word problems with process- and outcome-based feedback | Nov 25, 2022 | Arithmetic ReasoningGSM8K | —Unverified | 0 |
| PAL: Program-aided Language Models | Nov 18, 2022 | Arithmetic ReasoningGSM8K | CodeCode Available | 3 |
| Large Language Models Can Self-Improve | Oct 20, 2022 | Arithmetic ReasoningCommon Sense Reasoning | —Unverified | 0 |
