| AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations | Nov 22, 2023 | Common Sense ReasoningGSM8K | CodeCode Available | 0 |
| First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning | Nov 14, 2023 | GSM8KMath | —Unverified | 0 |
| SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks | Nov 14, 2023 | GSM8KMath | —Unverified | 0 |
| The ART of LLM Refinement: Ask, Refine, and Trust | Nov 14, 2023 | Arithmetic ReasoningGSM8K | —Unverified | 0 |
| Let's Reinforce Step by Step | Nov 10, 2023 | GSM8KLogical Reasoning | —Unverified | 0 |
| Prompt Engineering a Prompt Engineer | Nov 9, 2023 | counterfactualCounterfactual Reasoning | —Unverified | 0 |
| The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback | Oct 31, 2023 | GSM8KMMLU | —Unverified | 0 |
| SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving | Oct 19, 2023 | GSM8KMath | CodeCode Available | 0 |
| Let's reward step by step: Step-Level reward model as the Navigators for Reasoning | Oct 16, 2023 | Code GenerationGSM8K | —Unverified | 0 |
| DavIR: Data Selection via Implicit Reward for Large Language Models | Oct 16, 2023 | Causal Language ModelingGSM8K | —Unverified | 0 |
