Volume 15, Issue 6

Detectra-AI Response Hallucination Detector

Author

Dr. K. Prem Kumar, Pisupati Geetha Mahathi, Yadagiri Archita, S.Varshini, N.Sathyalaxmi, Mohd Zaheer

Abstract

Artificial intelligence systems are increasingly integrated into everyday applications, yet they often generate responses that are fluent but factually incorrect—a phenomenon known as hallucination. Such outputs reduce user trust and limit the reliability of AI-driven solutions in critical domains. To address this challenge, this study focuses on the design of a hallucination detection mechanism that can identify and flag unreliable AI responses in real time. By combining natural language processing techniques with verification strategies based on contextual consistency and factual alignment, the proposed detector evaluates the credibility of generated content before it reaches the end user. The approach emphasizes improving response accuracy, enhancing transparency, and supporting dependable AI usage across various tasks. This paper primarily discusses the concept of hallucination in AI, the need for detection systems, and how an automated detector can significantly improve the reliability and effectiveness of AI-generated outputs in practical environment.

Keywords: RPA, Artificial Intelligence (AI), Machine Learning (ML). Hallucination, Detectra

DOI: https://doi.org/10.62226/ijarst20262726

References:

Kohavi, R., Tang, D., and Xu, Y., 2020. Trustworthy Online Controlled Experiments: A Practical Guide to A/B Testing. Cambridge University Press.

Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y., Madotto, A. and Fung, P., 2023. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), pp.1–38.

OpenAI, 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774.

Rawte, V., Sheth, A. and Das, A., 2023. A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922

Thorne, J., Vlachos, A., Christodoulopoulos, C. and Mittal, A., 2018. FEVER: A large-scale dataset for fact extraction and verification. In Proceedings of NAACL-HLT, pp.809-819.

Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D. and Fung, P., 2023. A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023.

Maynez, J., Narayan, S., Bohnet, B. and McDonald, R., 2020. On faithfulness and factuality in abstractive summarization. In Proceedings of ACL, pp.1906-1919.

Shuster, K., Poff, S., Chen, M., Kiela, D. and Weston, J., 2021. Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567.

Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H. and others, 2023. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232.

Adadi, A. and Berrada, M., 2018. Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, pp.52138-52160.

DOI

https://doi.org/10.62226/ijarst20262726

PAGES : 2163-2168 | 12 VIEWS | 6 DOWNLOADS

Download Full Article