Phi-4 Technical Report

By Marah Abdin, Jyoti Aneja, Harkirat Singh Behl, Sébastien Bubeck, Ronen Eldan, S. Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann and 17 more. arXiv.org, 2024

716 citations recorded by the source corpus.

We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size -- especially on reasoning-focused benchmarks -- due to improved data, training curriculum, and innovations in the post-training scheme.

Subfields: Modeling and Simulation

View Paper: https://www.semanticscholar.org/paper/6485be47d22b7c2b07886af397c460e81f4d29a5

Citations in the corpus

• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs (2025, neutral): “Additionally, in the RoPE configuration [SAL + 24], a fractional RoPE dimension is used, ensuring that 25% of the attention head dimension remains position-agnostic.”
• Qwen3 Technical Report (2025, neutral): “5B and DeepSeek-R1-Distill-Llama-8B in the thinking mode, and Gemma-3-1B-IT, Phi-4-mini, Qwen2.”
• LLMs Get Lost In Multi-Turn Conversation (2025, neutral): “3-70B-Instruct, Llama 4 Scout) [23], AI2 OLMo-2-13B [56], Microsoft Phi-4 [1], Deepseek-R1 [24], and Cohere Command-A [15].”
• GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval (2026, unknown): “Models such as Llama 3.1 [13], Mistral 7B [15], Phi-4 [16], and Qwen 2.5 [14] demonstrate competitive performance at relatively small scales.”