Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language model (SLM) classifier for initial detection, followed by a LLM as constrained reasoner to generate detailed explanations for detected hallucinated content. This study optimizes the real-time interpretable hallucination detection by introducing effective prompting techniques that align LLM-generated explanations with SLM decisions. Empirical experiment results demonstrate its effectiveness, thereby enhancing the overall user experience.
@article{arxiv.2408.12748,
title = {SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection},
author = {Mengya Hu and Rui Xu and Deren Lei and Yaxi Li and Mingyu Wang and Emily Ching and Eslam Kamal and Alex Deng},
journal= {arXiv preprint arXiv:2408.12748},
year = {2024}
}