| AgentInstruct: Toward Generative Teaching with Agentic Flows | Jul 3, 2024 | GSM8KMMLU | —Unverified | 0 |
| Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs | Jul 1, 2024 | DiversityGSM8K | —Unverified | 0 |
| Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning | Jun 30, 2024 | GSM8KMath | CodeCode Available | 1 |
| Advancing Process Verification for Large Language Models via Tree-Based Preference Learning | Jun 29, 2024 | Binary ClassificationGSM8K | —Unverified | 0 |
| LiteSearch: Efficacious Tree Search for LLM | Jun 29, 2024 | GSM8KMathematical Reasoning | —Unverified | 0 |
| Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs | Jun 26, 2024 | Arithmetic ReasoningGSM8K | CodeCode Available | 3 |
| VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation | Jun 25, 2024 | ARCBenchmarking | CodeCode Available | 0 |
| PORT: Preference Optimization on Reasoning Traces | Jun 23, 2024 | ARCGSM8K | —Unverified | 0 |
| Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation | Jun 20, 2024 | GSM8KLanguage Model Evaluation | CodeCode Available | 0 |
| LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback | Jun 20, 2024 | Binary ClassificationGSM8K | CodeCode Available | 1 |
