Domain-specific question answering (QA) systems for services face unique challenges in integrating heterogeneous knowledge sources while ensuring both accuracy and safety. Existing large language models often struggle with factual consistency and context alignment in sensitive domains such as healthcare policies and government welfare. In this work, we introduce Knowledge-Aware Reasoning and Memory-Augmented Adaptation (KARMA), a novel framework designed to enhance QA performance in care scenarios. KARMA incorporates a dual-encoder architecture to fuse structured and unstructured knowledge sources, a gated memory unit to dynamically regulate external knowledge integration, and a safety-aware controllable decoder that mitigates unsafe outputs using safety classification and guided generation techniques. Extensive experiments on a proprietary QA dataset demonstrate that KARMA outperforms strong baselines in both answer quality and safety. This study offers a comprehensive solution for building trustworthy and adaptive QA systems in service contexts.

Domain-specific question answering (QA) systemsfor services face unique challenges in integrating heterogeneousknowledge sources while ensuring both accuracy and safety.Existing large language models often struggle with factual consistencyand context alignment in sensitive domains such ashealthcare policies and government welfare. In this work, weintroduce Knowledge-Aware Reasoning and Memory-AugmentedAdaptation (KARMA), a novel framework designed to enhanceQA performance in care scenarios. KARMA incorporates adual-encoder architecture to fuse structured and unstructuredknowledge sources, a gated memory unit to dynamically regulateexternal knowledge integration, and a safety-aware controllabledecoder that mitigates unsafe outputs using safety classificationand guided generation techniques. Extensive experiments on aproprietary QA dataset demonstrate that KARMA outperformsstrong baselines in both answer quality and safety. This studyoffers a comprehensive solution for building trustworthy andadaptive QA systems in service contexts.

This paper presents the Multimodal Language-Image Fusion Network (MLIF-Net), a new architecture to distinguish AI-generated images from real ones. MLIF-Net combines Vision Transformer (ViT) and Large Language Models (LLMs) to build a multimodal feature fusion network that improves AI-generated content detection accuracy. The model uses a Cross-Attention Mechanism to combine visual and semantic features and a Multiscale Contextual Reasoning Layer to capture both global and local image features. An Adaptive Loss Function improves the consistency and robustness of feature extraction. Experimental results show that MLIF-Net outperforms existing models in accuracy, recall, and Average Precision (AP). This approach can lead to more accurate detection of AI-generated content and may have applications in other generative content tasks.

Detecting AI-generated text is an important challenge, especially as large language models become better at creating content that looks like human writing. This paper presents a teacher-student framework to improve the performance and efficiency of short-context document classification. The framework uses domain adaptation and data augmentation to improve detection. The teacher model combines DeBERTa-v3-large and Mamba-790m models, using their fine-tuning on domain-specific data and semantic knowledge for accurate predictions. The student model works with short-context text of 128 and 256 tokens and learns from the teacher to balance accuracy and computational efficiency. To make the model more robust, we built a data generation and augmentation pipeline, applying techniques like spelling correction, character removal, and case flipping to increase data variety. The proposed framework outperforms current methods in accuracy and robustness, offering an efficient solution for detecting AI-generated text. This work also lays the groundwork for future studies on multilingual classification and real-time inference improvements in AI text detection.