Memory-Augmented Knowledge Fusion with Safety-Aware Decoding for Domain-Adaptive Question Answering

TL;DR

This paper presents KARMA, a novel framework that enhances domain-specific question answering by integrating heterogeneous knowledge sources with safety-aware decoding, improving accuracy and safety in sensitive applications.

Contribution

Introduces a dual-encoder, memory-augmented, safety-aware QA framework that effectively fuses knowledge sources and mitigates unsafe outputs in domain-specific settings.

Findings

Outperforms baselines in answer quality

Reduces unsafe outputs in QA responses

Enhances trustworthiness in sensitive domains

Abstract

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.