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

arXiv: https://arxiv.org/abs/2512.02363 · HTML: https://mlsanity.com/paper/2512.02363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 12 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 4 of 4)

- [Controlled Decoding from Language Models](https://mlsanity.com/paper/2310.17022/) (2023)
- [Enhancing Healthcare through Large Language Models: A Study on Medical Question Answering](https://mlsanity.com/paper/2408.04138/) (2024)
- [A Real-Time Adaptive Multi-Stream GPU System for Online Approximate Nearest Neighborhood Search](https://mlsanity.com/paper/2408.02937/) (2024)
- [Uncertainty Quantification in Table Structure Recognition](https://mlsanity.com/paper/2407.01731/) (2024)

## Abstract (arXiv)

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.