Home / Current Issue / Paper 1722609
Self-Reflective Large Language Models for Reducing AI Hallucinations: A Novel Framework for Reliable Generative AI
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: https://doi.org/10.64388/IREV10I2-1722609
Abstract
Large Language Models (LLMs) have become a central technology for generative artificial intelligence, but their tendency to produce fluent yet factually unsupported information remains a major barrier to dependable deployment. This paper proposes a self-reflective framework in which an LLM generates an answer, identifies claims that may be uncertain, performs an internal verification stage, and revises the response before delivery. Unlike a single-pass generation process, the proposed approach separates generation, claim inspection, evidence-oriented verification, and response refinement. The framework is designed to reduce unsupported claims while preserving useful information and acceptable response latency. The paper presents a research-oriented evaluation methodology using factuality, unsupported-claim rate, answer completeness, calibration, and computational overhead as evaluation dimensions. The proposed framework can be integrated with retrieval-augmented generation, external knowledge sources, or domain-specific validation modules. The study argues that self-reflection should be treated not merely as prompt engineering but as a structured reliability layer for generative AI systems.
Keywords
large language models, generative ai, ai hallucination, self-reflection, factuality, retrieval-augmented generation, llm reliability, artificial intelligence
References
[1] Lewis, P., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems.
[2] Ji, Z., et al. (2023). Survey of Hallucination in Natural Language Generation. ACM Computing Surveys.
[3] Madaan, A., et al. (2023). Self-Refine: Iterative Refinement with Self-Feedback. Advances in Neural Information Processing Systems.
[4] Shinn, N., Cassano, F., Labash, B., Gopinath, A., & Yao, S. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. Advances in Neural Information Processing Systems.
[5] Asai, A., et al. (2024). Self-RAG: Learning to Retrieve, Generate, and Critique through Self- Reflection. International Conference on Learning Representations.
[6] Manakul, P., Liusie, A., & Gales, M. (2023). SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models. Proceedings of EMNLP.
[7] OpenAI. (2023). GPT-4 Technical Report. arXiv preprint arXiv:2303.08774.
[8] Touvron, H., et al. (2023). LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971.
How to cite this paper
@article{1722609,
author = {Priti Sharma, Sachin Sharma},
title = {Self-Reflective Large Language Models for Reducing AI Hallucinations: A Novel Framework for Reliable Generative AI},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {3068-3072},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1722609.pdf},
abstract = {Large Language Models (LLMs) have become a central technology for generative artificial intelligence, but their tendency to produce fluent yet factually unsupported information remains a major barrier to dependable deployment. This paper proposes a self-reflective framework in which an LLM generates an answer, identifies claims that may be uncertain, performs an internal verification stage, and revises the response before delivery. Unlike a single-pass generation process, the proposed approach separates generation, claim inspection, evidence-oriented verification, and response refinement. The framework is designed to reduce unsupported claims while preserving useful information and acceptable response latency. The paper presents a research-oriented evaluation methodology using factuality, unsupported-claim rate, answer completeness, calibration, and computational overhead as evaluation dimensions. The proposed framework can be integrated with retrieval-augmented generation, external knowledge sources, or domain-specific validation modules. The study argues that self-reflection should be treated not merely as prompt engineering but as a structured reliability layer for generative AI systems.},
keywords = {large language models, generative ai, ai hallucination, self-reflection, factuality, retrieval-augmented generation, llm reliability, artificial intelligence},
month = {August},
doi = {https://doi.org/10.64388/IREV10I2-1722609}
}