SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
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.
Code (1)
Tasks
HallucinationLanguage ModelingLanguage ModellingSmall Language ModelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models
Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this…
Reallocating Attention Across Layers to Reduce Multimodal Hallucination
Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between perception and reasoning processes. Building up…
Multimodal ReasoningVisual GroundingCIP: A Plug-and-Play Causal Prompting Framework for Mitigating Hallucinations under Long-Context Noise
Large language models often hallucinate when processing long and noisy retrieval contexts because they rely on spurious correlations rather than genuine causal relationships. We propose CIP, a lightweight and plug-and-pl…
Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction
We introduce CAROL (Chain-based Adaptive Reconfiguration Over Lattices), a probabilistic framework for test-time hallucination reduction in large language models. Rather than relying on token-level uncertainty, CAROL def…
Computational EfficiencyQuestion AnsweringTuning for Trustworthiness -- Balancing Performance and Explanation Consistency in Neural Network Optimization
Despite the growing interest in Explainable Artificial Intelligence (XAI), explainability is rarely considered during hyperparameter tuning or neural architecture optimization, where the focus remains primarily on minimi…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Model Selection