| Octopus v4: Graph of language models | Apr 30, 2024 | MMLU | —Unverified | 0 |
| OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning | Feb 16, 2025 | MedQAMMLU | —Unverified | 0 |
| On the Reasoning Capacity of AI Models and How to Quantify It | Jan 23, 2025 | MemorizationMMLU | —Unverified | 0 |
| OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models | Feb 29, 2024 | Medical Question AnsweringMedQA | —Unverified | 0 |
| Optimised Grouped-Query Attention Mechanism for Transformers | Jun 21, 2024 | MMLU | —Unverified | 0 |
| Order Independence With Finetuning | Mar 30, 2025 | ARCLanguage Modeling | —Unverified | 0 |
| ORI: O Routing Intelligence | Feb 14, 2025 | ARCMMLU | —Unverified | 0 |
| Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone | Apr 22, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback | Jun 21, 2024 | Information RetrievalLearning-To-Rank | —Unverified | 0 |
| PolyPrompt: Automating Knowledge Extraction from Multilingual Language Models with Dynamic Prompt Generation | Feb 27, 2025 | MMLU | —Unverified | 0 |
