Aug 2026· International Journal For Multidisciplinary Research· 0 citations· 13 references
TL;DR
This paper presents an adaptive knowledge-augmented framework for Mizo Large Language Models by combining Retrieval-Augmented Generation (RAG) with continual learning that harnesses semantic retrieval with dense embeddings and FAISS indexing, adaptive evidence re-ranking, parameter-efficient fine-tuning, and incremental knowledge updating to enhance factual accuracy and decrease hallucinations.
Abstract
The deployment of Large Language Models (LLMs) for low-resource languages is challenging due to the lack of linguistic resources, sparse digital content and the absence of structured knowledge bases. In this paper, we present an adaptive knowledge-augmented framework for Mizo Large Language Models by combining Retrieval-Augmented Generation (RAG) with continual learning. This methodology harnesses semantic retrieval with dense embeddings and FAISS indexing, adaptive evidence re-ranking, parameter-efficient fine-tuning, and incremental knowledge updating to enhance factual accuracy and decrease hallucinations. Experimental evaluation shows better retrieval performance, greater text creation quality, and superior human evaluation scores than typical multilingual LLMs and static RAG methods. Moreover, the continual learning technique allows for effective integration of newly accessible Mizo resources, without re-training the model from scratch. The suggested architecture offers a scalable, stable and reusable method for the development of intelligent language technologies for Mizo and other low-resource languages.
Large language models have accelerated the development of intelligent assistants by providing flexible natural- language understanding and generation. However, hallucination, knowledge staleness, and limited coverage of domain-specific information continue to restrict their reliability in knowledge-intensive tasks. This review examines how Retrieval -Augmented Generation (RAG) can strengthen LLM-based intelligent assistants by connecting generative capability with external, maintainable knowledge. It synthesi zes research on the technical foundations of RAG, key components and optimization strategies, and applications and challenges in intelligent-assistant settings. The review finds that RAG can improve knowledge accuracy and timeliness by grounding responses in retrieved evidence and allowing knowledge resources to be updated independently of the base model. These benefits are conditional: unreliable retrieval, poorly maintained sources, ineffective use of context, and fragmented evaluation can still produce u nsupported or unsafe answers. Reliable deployment, therefore, requires coordinated retrieval quality, knowledge management, generation control, and trustworthy evaluation. Future RAG-based assistants should combine these capabilities to become scalable, secure, evidence-aware, and verifiable systems.
The evidence indicates that no single RAG or vector-database configuration dominates across retrieval quality, faithfulness, latency, throughput, storage, cost, and scalability, and the review positions RAG–vector database integration as a joint retrieval-and-systems optimization problem rather than a database-selection problem alone.
Muhammad Fuad Bin Abdullah, Safwan Abd Razak, Noorrezam Yusop et al.· International journal of res...· 0 citations
A novel approach to Intelligent Tutoring Systems (ITS) is presented by integrating Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) to enable dynamic personalization in educational contexts by implementing a three-layered architecture combining semantic retrieval mechanisms with generative AI capabilities.
Kuyoro Afolashade, N. Uchenna, Akinwunmi Damilare· British journal of computer,...· 0 citations
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external information, but traditional fixed retrieval processes struggle to adapt to complex task requirements. In recent years, reinforcement learning (RL) has been increasingly applied to train LLMs to autonomously invoke search tools, driving RAG to evolve from the passive information acquisition of a fixed pipeline to a trustworthy retrieval system with autonomous decision-making capabilities. This paper reviews the representative studies on the combination of LLMs, RAG and RL in recent years. It focuses on analyzing the role of RL in dynamic retrieval, process rewards, query optimization, etc., and compares the connections and evolutionary relationships among different methods. The research findings show that RL has gradually expanded from simply improving the accuracy of the final answer to optimizing queries, multi-round search, process decision-making and trustworthy screening, providing new ideas for enhancing the active retrieval ability of RAG and improving the credibility of information.
Zun-Long Hong· Applied and Computational En...· 0 citations
Experimental results show that SAC-RAG reduces token consumption by 38%–58% at the cost of only a 1–2 percentage point EM drop, with EM actually improving after compression for reasoning-type questions, achieving the optimal quality–efficiency trade-off in terms of token consumption.
Deyu Zhang, Hongqiang Yu, Jinze Huo et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
