@article{4754,
  author = {Maleerat Sodanil},
  title = {The Double-Lock Framework: A Multi-Layered System for Grounded Retrieval-Augmented Generation and Hallucination Mitigation},
  journal = {International Journal of Computational Linguistics Research},
  year = {2026},
  volume = {17},
  number = {2},
  doi = {https://doi.org/10.6025/ijclr/2026/17/2/100-126},
  url = {https://www.dline.info/jcl/fulltext/v17n2/jclv17n2_3.pdf},
  abstract = {Retrieval-Augmented Generation (RAG) systems have significantly improved the factual grounding of large
language models (LLMs). However, challenges remain in ensuring both semantic correctness and transparent
attribution, as models may still produce hallucinated or unverified outputs. This paper proposes the Double-
Lock Framework, a multi-layered architecture that integrates data engineering, linguistic attribution
modeling, and dual validation mechanisms to mitigate hallucinations. A high-fidelity “Gold Standard” dataset
is constructed using strict filtering criteria based on factual consistency and hallucination labels. The
framework introduces attribution markers to enhance interpretability and employs both supervised finetuning
and reward-based optimization for model training. A two-stage validation mechanism combining
regex-based linguistic checks and predictive AI scoring ensures both transparency and factual accuracy.
Experimental evaluation on a 6,000-sample dataset demonstrates that while regex-based validation alone
results in a 7.72% hallucination leakage rate, the proposed Double-Lock mechanism achieves 0% leakage.
The framework effectively bridges the gap between retrieval and human-understandable knowledge
synthesis, enabling the development of reliable and trustworthy AI systems.},
}