mlsanityData to 7 Oct 2026

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

arXiv 2404.14219 ↗First posted 22 Apr 2024cs.CL cs.AIcited by 1,883

Not on the map. Why?

Cited by 379 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38 on MT-bench), despite being small enough to be deployed on a phone. Our training dataset is a scaled-up version of the one used for phi-2, composed of heavily filtered publicly available web data and synthetic data. The model is also further aligned for robustness, safety, and chat format. We also provide parameter-scaling results with a 7B, 14B models trained for 4.8T tokens, called phi-3-small, phi-3-medium, both significantly more capable than phi-3-mini (e.g., respectively 75%, 78% on MMLU, and 8.7, 8.9 on MT-bench). To enhance multilingual, multimodal, and long-context capabilities, we introduce three models in the phi-3.5 series: phi-3.5-mini, phi-3.5-MoE, and phi-3.5-Vision. The phi-3.5-MoE, a 16 x 3.8B MoE model with 6.6 billion active parameters, achieves superior performance in language reasoning, math, and code tasks compared to other open-source models of similar scale, such as Llama 3.1 and the Mixtral series, and on par with Gemini-1.5-Flash and GPT-4o-mini. Meanwhile, phi-3.5-Vision, a 4.2 billion parameter model derived from phi-3.5-mini, excels in reasoning tasks and is adept at handling both single-image and text prompts, as well as multi-image and text prompts.

Key facts. Cited by 1,883 papers in the map (data through 7 Oct 2026). Builds on 52 of its 64 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

52 of 64 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Scaling Laws for Neural Language Modelscited by 6,411
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  11. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  12. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
38 more
  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  7. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  8. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  11. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  12. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  13. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  14. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  15. 2019Towards VQA Models That Can Readcited by 1,696
  16. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  17. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  18. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  19. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  20. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  21. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  22. 2016A Diagram Is Worth A Dozen Imagescited by 793
  23. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  24. 2023Textbooks Are All You Needcited by 561
  25. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  26. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  27. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  28. 2023Scaling Data-Constrained Language Modelscited by 391
  29. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 377
  30. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  31. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  32. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 302
  33. 2022Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfercited by 272
  34. 2024MM1: Methods, Analysis & Insights from Multimodal LLM Pre-trainingcited by 230
  35. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 160
  36. 2024InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HDcited by 156
  37. 2024Red Teaming Visual Language Modelscited by 62
  38. 2023Bridging Discrete and Backpropagation: Straight-Through and Beyondcited by 31

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 631; 2025: 913; 2026: 339.

1,883 papers.

Sort:

By area:

  1. 2024Qwen2.5 Technical Reportcited by 4,713
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  3. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  4. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  5. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  6. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  7. 2024A Survey on Large Language Models for Code Generationcited by 646
  8. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 644
  9. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 559
  10. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  11. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  12. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 491
38 more
  1. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  2. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 443
  3. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  4. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  5. 2024OmniGen: Unified Image Generationcited by 388
  6. 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attentioncited by 375
  7. 2024Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothingcited by 341
  8. 2024LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understandingcited by 341
  9. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 321
  10. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  11. 2024Latent Action Pretraining from Videoscited by 302
  12. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  13. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 291
  14. 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
  15. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 281
  16. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  17. 2025Small Language Models are the Future of Agentic AIcited by 254
  18. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 242
  19. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  20. 2024ShowUI: One Vision-Language-Action Model for GUI Visual Agentcited by 226
  21. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 225
  22. 2024OR-Bench: An Over-Refusal Benchmark for Large Language Modelscited by 222
  23. 2024VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Taskscited by 222
  24. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 211
  25. 2024A Careful Examination of Large Language Model Performance on Grade School Arithmeticcited by 188
  26. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  27. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  28. 2024Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modelingcited by 167
  29. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  30. 2024Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Datasetcited by 153
  31. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 146
  32. 2025Phi-4-reasoning Technical Reportcited by 146
  33. 2024Vision language models are blind: Failing to translate detailed visual features into wordscited by 144
  34. 2024Compact Language Models via Pruning and Knowledge Distillationcited by 142
  35. 2024LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMscited by 142
  36. 2024How to Train Long-Context Language Models (Effectively)cited by 141
  37. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 137
  38. 2024Adam-mini: Use Fewer Learning Rates To Gain Morecited by 134

50 most cited of 1,883 All 1,883 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
  2. 2022Prompting GPT-3 To Be Reliable
  3. 2023Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording
  4. 2025Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models
  5. 2024SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
  6. 2024Telecom Language Models: Must They Be Large?
  7. 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
  8. 2025Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation