Saved in:
Bibliographic Details
Main Authors: Hu, Mengya, Xu, Rui, Lei, Deren, Li, Yaxi, Wang, Mingyu, Ching, Emily, Kamal, Eslam, Deng, Alex
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.12748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914921345712128
author Hu, Mengya
Xu, Rui
Lei, Deren
Li, Yaxi
Wang, Mingyu
Ching, Emily
Kamal, Eslam
Deng, Alex
author_facet Hu, Mengya
Xu, Rui
Lei, Deren
Li, Yaxi
Wang, Mingyu
Ching, Emily
Kamal, Eslam
Deng, Alex
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12748
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
Hu, Mengya
Xu, Rui
Lei, Deren
Li, Yaxi
Wang, Mingyu
Ching, Emily
Kamal, Eslam
Deng, Alex
Computation and Language
Artificial Intelligence
Machine Learning
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.
title SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.12748