Interactive AI Conversation Using Small Language Model (SLM) Chatbot

References

[1] A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998–6008.

[2] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.

[3] T. B. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2020, pp. 1877–1901.

[4] A. Radford et al., “Improving Language Understanding by Generative Pre-Training,” OpenAI, 2018.

[5] Y. Liu et al., “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” arXiv preprint arXiv:1907.11692, 2019.

[6] T. Wolf et al., “Transformers: State-of-the-Art Natural Language Processing,” in Proc. 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2020, pp. 38–45.

[7] C. Raffel et al., “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” Journal of Machine Learning Research, vol. 21, no. 140, pp. 1–67, 2020.

[8] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

[9] A. M. Turing, “Computing Machinery and Intelligence,” Mind, vol. 59, no. 236, pp. 433–460, 1950.

[10] T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, “Distributed Representations of Words and Phrases and their Compositionality,” in Advances in Neural Information Processing Systems (NeurIPS), 2013, pp. 3111–3119.

[11] M. Chen et al., “Evaluating Large Language Models Trained on Code,” arXiv preprint arXiv:2107.03374, 2021.

[12] S. Min et al., “Recent Advances in Large Language Models,” ACM Computing Surveys, vol. 56, no. 9, 2024.

[13] M. Bommasani et al., “On the Opportunities and Risks of Foundation Models,” arXiv preprint arXiv:2108.07258, 2021.

[14] Z. Li et al., “Small Language Models: Survey, Measurements, and Insights,” arXiv preprint, 2024.

[15] J. Wei et al., “Emergent Abilities of Large Language Models,” Transactions on Machine Learning Research (TMLR), 2022.

@article{1719389,
      author = {T Priya, I Esther Praishe},
      title = {Interactive AI Conversation Using Small Language Model (SLM) Chatbot},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {12},
      pages = {3077-3079},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719389.pdf},
      abstract = {Conversational Artificial Intelligence (AI) has transformed human–computer interaction by enabling intelligent, context-aware, and natural communication. However, most chatbot systems rely on Large Language Models (LLMs), which demand significant computational resources, memory, and cloud infrastructure. This paper presents an Interactive AI Conversation System based on a Small Language Model (SLM) chatbot that provides efficient, low-latency, and cost-effective conversational capabilities. The proposed system employs natural language processing (NLP), transformer-based SLM architecture, intent recognition, contextual memory, and response generation to deliver interactive conversations while operating with significantly lower computational requirements. The chatbot is designed for educational assistance, customer support, healthcare guidance, and enterprise applications. Experimental evaluation demonstrates reduced inference latency, lower memory consumption, and competitive conversational quality, making the proposed system suitable for deployment on edge devices and resource-constrained environments. Small Language Models are increasingly attractive because they provide lower latency and lower resource usage while remaining effective for many specialized conversational tasks.},
      keywords = {Small Language Model, Chatbot, Artificial Intelligence, Natural Language Processing, Transformer, Conversational AI, Edge Computing.},
      month = {June},
      doi = {https://doi.org/10.64388/IREV9I12-1719389}
  }