Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174220,
        author = {Enikepalli jithendra Venkata Varun and Dr. S. Jagadeesan and Vainika Siripurapu},
        title = {Leveraging Large Language Models for Semi-Structured Conversational Recommendations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {3629-3636},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174220},
        abstract = {Large Language Models (LLMs) have revolutionized the field of natural language processing, offering unprecedented capabilities for understanding and generating human-like text. This paper explores their application in building a semi-structured conversational recommendation system that balances open-ended dialogue with goal-oriented interaction. Unlike fully structured systems that rely on predefined scripts or purely open-ended ones that lack direction, a semi-structured approach integrates the flexibility of natural conversation with the precision of structured queries. By leveraging the contextual understanding and reasoning capabilities of LLMs, the proposed system can adaptively guide users through personalized recommendations while maintaining an engaging conversational flow. Key challenges addressed include maintaining coherence in dynamic conversations, managing user intent ambiguity, and ensuring relevance in recommendations. The study employs advanced LLM architectures, fine-tuned on domain-specific data, to deliver tailored recommendations across diverse industries, such as e-commerce, healthcare, and entertainment. Evaluations highlight the system’s effectiveness in enhancing user satisfaction, improving recommendation relevance, and increasing interaction efficiency compared to traditional systems. This research underscores the transformative potential of LLMs in redefining how recommendation systems interact with users, paving the way for smarter, more intuitive, and user-centric conversational interfaces.},
        keywords = {Large Language Models (LLMs), Conversational AI, Recommendation Systems, Semi-Structured Conversations, Natural Language Processing (NLP)},
        month = {March},
        }