5 papers
AI-Assisted Knowledge Access for Legacy Enterprise Asset Management in Energy Operations: A Practical Retrieval System
Dave Mercier, Mishca de Costa, Muhammad Anwar +2
Energy utilities still run engineering work management, engineering procurement, and inventory processes on long-lived enterprise asset management platforms. Replacing these platfo…
From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance
Mishca de Costa, Muhammad Saleh Anwar, Dave Mercier +1
Retrieval-augmented generation (RAG) is the dominant paradigm for applying large language models (LLMs) to enterprise document corpora, yet naive implementations encounter hard lim…
Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL
Mishca de Costa, Muhammad Anwar, Dave Mercier +2
Retrieving operational data from nuclear power plants requires exceptional accuracy and transparency due to the criticality of the decisions it supports. Traditionally, natural lan…
Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data
Muhammad Anwar, Daniel Lau, Mishca de Costa +1
The nuclear industry possesses a wealth of valuable information locked away in unstructured text data. This data, however, is not readily usable for advanced Large Language Model (…
Towards Secure and Private Language Models for Nuclear Power Plants
Muhammad Anwar, Mishca de Costa, Issam Hammad +1
This paper introduces a domain-specific Large Language Model for nuclear applications, built from the publicly accessible Essential CANDU textbook. Drawing on a compact Transformer…