Citation :

Vaishnavi Visweswaraiah, "Everyday AI: Real-World Applications of Transformer Based Language Models," International Journal of Computer Trends and Technology (IJCTT), vol. 73, no. 9, pp. 19-27, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I9P103

Abstract

Artificial Intelligence (AI) systems called Large Language Models (LLMs), powered by transformer architectures, have become integral to everyday digital interactions. Although we may not always notice them, these models are used directly or indirectly on many platforms. Well-known models such as Gemini, GPT, T5, and Llama are used in search engines, recommendation systems, social media, and conversational assistants. This article reviews three transformer architectures (encoder-decoder, encoder-only, and decoder-only) that enable computers to understand language, perform translation, generate content, and provide personalized suggestions by mapping it to real-world implementations, such as YouTube Music, Google Search, DoorDash, Netflix, Uber, and many others by highlighting the underlying models, their associated transformer architectures, and their functionalities. This article aims to promote AI literacy and improve understanding of how LLMs shape daily digital experiences. 

Keywords

Artificial Intelligence, Large Language Model, Transformer, Architecture, GPT, Llama, Gemini.

References

[1] Xavier Amatriain et al., “Transformer Models: An Introduction and Catalog, arXiv preprint arXiv:2302.07730, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2]  Ashish Vaswani et al., “Attention Is All You Need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
[Google Scholar]

[3] Meet Your New Assistant: Meta AI, Built with Llama 3, 2024. [Online]. Available: https://about.fb.com/news/2024/04/meta-ai-assistant-built-with-llama-3/

 [4] Pandu Nayak, Understanding Searches Better than Ever Before, 2019. [Online]. Available: https://blog.google/products/search/search-language-understanding-bert/

[5] Boyu Liu, “Comparative Analysis of Encoder-Only, Decoder-Only, and Encoder- Decoder Language Models,” International Conference on Data Science and Engineering, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Andrea Filippo Ferraris et al., “The Architecture of Language: Understanding the Mechanics Behind LLMs,” Cambridge forum on AI: Law and governance, vol. 1, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Dasom Choi et al., “Unlock Life with a Chat(GPT): Integrating Conversational AI with Large Language Models into Everyday Lives of Autistic Individuals,” Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1–17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Nada Terzimehić, Babette Bühler, and Enkelejda Kasneci, “Conversational AI as a Catalyst for Informal Learning: An Empirical Large-Scale Study on LLM Use in Everyday Learning,” arXiv e-prints, arXiv-2506,2025.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Gabriele Civitarese et al., “Large Language Models Are Zero-Shot Recognizers for Activities of Daily Living,” ACM Transactions on Intelligent Systems and Technology, vol. 16, no. 4, pp. 1–32, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Michael Sonntagbauer, Markus Haar, and Stefan Kluge, “Artificial Intelligence: How will ChatGPT and Other AI Applications Change our Everyday Medical Practice?,” Medical Clinic, Intensive Care and Emergency Medicine, vol. 118, no. 5, pp. 366–371, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Nina Perry et al., “AI Technology to Support Adaptive Functioning in Neurodevelopmental Conditions in Everyday Environments: A Systematic Review,” npj Digital Medicine, vol. 7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Marjona Aslitdinova, “How Artificial Intelligence Helps us in Our Daily Life,” International Journal of Artificial Intelligence, vol. 1, no. 4, pp. 538–542, 2025.
[Google Scholar] [Publisher Link]

[13] Santigo Canchila et al., “Natural Language Processing: An Overview of Models, Transformers and Applied Practices,” Computer Science and Information Systems, vol. 21, no. 3, pp. 1097–1145, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Xuchuan Li et al., “Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles,” arXiv e-prints, arXiv-2407, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Yu Ying Chiu, Liwei Jiang, and Yejin Choi, “Dailydilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life,” arXiv preprint arXiv:2410.02683, 2024. 
[CrossRef] [Google Scholar] [Publisher Link]

[16] Gaole He, Gianluca Demartini, and Ujwal Gadiraju, “Plan-then-execute: An Empirical Study of user Trust and Team Performance When using LLM Agents as a Daily Assistant,” Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pp. 1-22, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Haruki Yonekura et al., “Generating Human Daily Activities with LLM for Smart Home Simulator Agents,” 2024 International Conference on Intelligent Environments (IE), 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Mathyas Giudici et al., “Designing Home Automation Routines using an LLM-based Chatbot,” Designs, vol. 8, no. 3, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Jingping Nie et al., “LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention Via Everyday Smart Devices,” arXiv preprint arXiv:2403.10779, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Wenqi Zheng, and Yutaka Arakawa, “A Review of Wearables-Based Activities of Daily Living Recognition with LLMs: Overview, Progress and Trends,” IEEE Access, vol. 13, pp. 143813-143830, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Muhammad Usman Hadi et al., “Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects,” Authorea preprints, vol. 1, no. 3, pp. 1-26.
[Google Scholar]

[22] Jay Alammar, The Illustrated Transformer,2018. [Online].

Available: https://jalammar.github.io/illustrated-transformer/

[23] Chintalwar Adhik, Sonti Sri Lakshmi, and C. Muralidharan, “Text Summarization using BART,” AIP Conference Proceedings, vol. 3075, no. 1. 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Glory Odeyemi, “Finetuning Encoder-Decoder Transformer Models for Text Summarization using Pause Tokens,” University of Windsor, Ontario, Canada, 2025.
[Google Scholar] [Publisher Link]

[25] Saleh Soltan et al., AlexaTM 20B: Few-shot Learning using a Large-scale Multilingual seq2seq Model, 2025. [Online].

Available: https://www.amazon.science/publications/alexatm-20b-few-shot-learning-using-a-large-scale-multilingual-seq2seq-model

[26] Pandu Nayak, MUM: A New AI Milestone for Understanding Information, 2021. [Online].

Available: https://blog.google/products/search/introducing-mum/

[27] Sundar Pichai, and Demis Hassabis, Introducing Gemini: Our Largest and Most Capable AI Model, 2023. [Online].

Available: https://blog.google/technology/ai/google-gemini-ai/

[28] Robby Stein, Expanding AI Overviews and Introducing AI Mode, 2025. [Online].

Available: https://blog.google/products/search/ai-mode-search/

[29]  AI Advances to Better Detect Hate Speech, 2020. [Online].

Available: https://ai.meta.com/blog/ai-advances-to-better-detect-hate-speech/

 [30] Yinhan Liu et al., “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” arXiv preprint arXiv:1907.11692, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Hugo Touvron et al., “LLaMA: Open and Efficient Foundation Language Models,” arXiv preprint arXiv:2302.13971, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Introducing New AI Experiences Across Our Family of Apps and Devices, 2023. [Online].

Available: https://about.fb.com/news/2023/09/introducing-ai-powered-assistants-characters-and-creative-tools/

[33] Introducing Meta Llama 3: The Most Capable Openly Available LLM to Date, 2024. [Online].

Available: https://ai.meta.com/blog/meta-llama-3/

[34] Anushya Subbiah, and Vikram Agarwal, Transformers in Music Recommendation, 2024. [Online].

Available: https://research.google/blog/transformers-in-music-recommendation/

[35] Ko-Jen Hsiao, Yesu Feng, and Sudarshan Lamkhede, Foundation Model for Personalized Recommendation, 2025. [Online].

Available: https://netflixtechblog.com/foundation-model-for-personalized-recommendation-1a0bd8e02d39

[36] Zachary Cavanell, “Microsoft 365 Copilot Wave 2 Spring Updates, 2025. [Online].

Available: https://techcommunity.microsoft.com/blog/microsoftmechanicsblog/microsoft-365-copilot-wave-2-spring-updates/4414785

[37] Microsoft 365 Copilot Release Notes, 2025. [Online].

Available: https://learn.microsoft.com/en-us/copilot/microsoft-365/release-notes

[38] Colette Stallbaumer, Introducing Copilot for Microsoft 365, 2023. [Online].

Available: https://www.microsoft.com/en-us/microsoft-365/blog/2023/03/16/introducing-microsoft-365-copilot-a-whole-new-way-to-work/

[39] Newsroom, Early Insights on My AI. [Online].

Available: https://newsroom.snap.com/early-insights-on-my-ai

[40] What is My AI on Snapchat and How do I use It?. [Online].

Available: https://help.snapchat.com/hc/en-us/articles/13266788358932-What-is-My-AI-on-Snapchat-and-how-do-I-use-it

[41] Praveen Kumar Bodigutla, How we Built Domain-adapted Foundation GenAI Models to Power Our Platform, 2024. [Online].

Available: https://www.linkedin.com/blog/engineering/generative-ai/how-we-built-domain-adapted-foundation-genai-models-to-power-our-platform

[42] Introducing Llama 3.1: Our Most Capable Models to Date, 2024. [Online].

Available: https://ai.meta.com/blog/meta-llama-3-1/

[43] Parker Henry, How Duolingo uses AI to Create Lessons Faster, 2023. [Online].

Available: https://blog.duolingo.com/large-language-model-duolingo-lessons/

[44] Parker Henry, Get to Know the AI Behind Every Video Call with Lily, 2025. [Online].

Available: https://blog.duolingo.com/ai-and-video-call/

[45] OpenAI, Uber Enables Outstanding On-demand Experiences with AI, 2025. [Online].

Available: https://openai.com/index/uber-enables-outstanding-experiences/

[46] Bo Ling et al., Open Source and In-House: How Uber Optimizes LLM Training, 2024. [Online].

Available: https://www.uber.com/en-EG/blog/open-source-and-in-house-how-uber-optimizes-llm-training/

[47] Mistral AI team, Mixtral of Experts, 2023. [Online].

Available: https://mistral.ai/news/mixtral-of-experts

[48] Elevate Your Productivity and Creativity with Generative AI, 2025. [Online].

Available: https://www.grammarly.com/ai/generative-ai

[49] Vipul Raheja et al., “CoEdIT: Text Editing by Task-Specific Instruction Tuning,” arXiv preprint arXiv:2305.09857, 2023.

[CrossRef] [Google Scholar] [Publisher Link]

[50] Vipul Raheja et al., “mEdIT: Multilingual Text Editing via Instruction Tuning,” arXiv preprint arXiv:2402.16472, 2024.

[CrossRef] [Google Scholar] [Publisher Link]

[51] Sudeep Das, Unleashing the Power of Large Language Models at DoorDash for a Seamless Shopping Adventure, 2024. [Online].

Available: https://careersatdoordash.com/blog/unleashing-the-power-of-large-language-models-at-doordash-for-a-seamless-shopping-adventure/

[52] Sissie Hsiao, Bard Becomes Gemini: Try Ultra 1.0 and A New Mobile App Today, 2024. [Online].

[53] Steven Xu, and Sree Chaitanya Vadrevu, Building DoorDash’s Product Knowledge Graph with Large Language Models, 2024. [Online]. Available: https://careersatdoordash.com/blog/building-doordashs-product-knowledge-graph-with-large-language-models