Anirban Saha Anik

Anirban Saha Anik

he/him

MS Data Science @ University of North Texas | LLM Researcher

Anik’s Curriculum Vitae

Research Interests

My research focuses on Natural Language Processing (NLP) and Large Language Models (LLMs) with interests in retrieval-augmented generation (RAG), health misinformation detection, and fact-grounded communication. I aim to build context-aware, interpretable, and socially responsible AI systems for critical domains like public health and crisis response. My goal is to design adaptive, human-aligned models that support decision-making, trust, and effective communication.

Education

University of North Texas, Denton, TX
M.S. in Data Science — GPA: 4.0/4.0 (Expected Dec 2025)

American International University-Bangladesh, Dhaka
B.Sc. in Computer Science and Engineering — CGPA: 3.59/4.0 (Dec 2021)

Technical Skills

  • NLP & LLMs: Transformers, Hugging Face, Retrieval-Augmented Generation (RAG), LoRA, LLaMA, GPT, Mistral, RLHF
  • Programming: Python, R
  • Libraries & Frameworks: PyTorch, TensorFlow, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn
  • Data & Visualization: SQL, Tableau, Power BI, Excel, Plotly
  • Tools & Platforms: Git, Weights & Biases, Streamlit, Jupyter, LaTeX, Linux

Work Experience

Graduate Research Assistant

University of North Texas, Denton, TX (May 2025 – Present)

  • Research under Dr. Lingzi Hong on LLM-based counter-speech generation for combating health misinformation
  • Designed multi-agent RAG frameworks for personalized, fact-grounded public messaging

Graduate Teaching Assistant

University of North Texas, Denton, TX (Aug 2024 – May 2025)

  • Supported INFO 4709 (Data Visualization) and Intro to Data Science (R, ML, EDA)
  • Assisted with lectures, grading, and student mentoring

Research Assistant

KI Research Lab, AIUB, Dhaka, Bangladesh (May 2022 – Dec 2022)

  • Deep learning research on medical data for disease classification
  • Assisted literature reviews and mentored undergrad research

Intern – Enterprise Applications

BRAC Microfinance, Dhaka, Bangladesh (Mar 2022 – May 2022)

  • Conducted UAT and field-based usability research for internal tools

Teaching Assistant

AIUB, Dhaka, Bangladesh (Sep 2021 – Dec 2021)

  • Assisted in the Introduction to Database course (SQL, schema design)

Publications

  • Dynamic Fusion of Large Language Models for Crisis Communication
    Xiaoying Song, Anirban Saha Anik, Vanessa Frías-Martínez, Lingzi Hong
    International Conference on Information Systems for Crisis Response and Management (ISCRAM), 2025
    DOI: 10.59297/nqysjq45

  • A Hybrid Attention-Guided Fusion Network with Grad-CAM for MPox Skin Lesion Classification
    Mithila Arman, Naheyan Prottush, Maher Ali Rusho, Arup Datta, Anirban Saha Anik, Din Mohammad Dohan, Md. Ashiq Ul Islam Sajid, Intezab Alam Sheikh, Md. Khurshid Jahna
    4th International Conference on Computing and Machine Intelligence (ICMI), 2025 (Accepted)

  • Outcome-Based Education: Evaluating Students’ Perspectives Using Transformer
    Shuvra Smaran Das, Anirban Saha Anik, Md. Kishor Morol, Mohammad Sakib Mahmood
    27th International Conference on Computer and Information Technology (ICCIT), 2024
    DOI: 10.1109/ICCIT64611.2024.11021724

  • A Study on Future Lockdown Predictions Using ANN
    Shuvra Smaran Das, Anirban Saha Anik, Md. Muzakker Hossain, Md. Kishor Morol, Fariha Jahan, Md. Abdullah-Al-Jubair
    International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM), 2023
    DOI: 10.1109/NCIM59001.2023.10212686

  • A Comparative Analysis for the Detection of COVID-19 from Chest X-ray Dataset
    Anirban Saha Anik, Kowshik Chakraborty, Bishowjit Datta, Abdul Kader, Md. Kishor Morol
    International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), 2022
    DOI: 10.1109/ICRPSET57982.2022.10188570

Research Projects

  • A Multi-Agent Framework for Evidence-Grounded Counterspeech in Health Contexts
    Designing modular agents for retrieval, prompting, and reasoning to support LLM-generated counterspeech (Under Review)

  • TeamX at CLEF 2025: Prompted vs. Fine-Tuned LLMs for Numerical Claim Verification
    Comparing zero-shot prompting vs. supervised fine-tuning with LoRA for fact-checking (Under Review)

  • Controlled Counterspeech for Health Literacy Levels
    Developing personalized responses using LLaMA/GPT conditioned on user health literacy (Under Review)

  • Dynamic Model Fusion for Crisis Response
    Exploring multi-model strategies to ensure contextual consistency in LLM outputs (Under Review)

  • Integrating Real-Time Context into LLMs
    Live entity extraction + RAG-based generation for real-time crisis response (Ongoing)

Projects

  • Enhancing Early Alzheimer’s Detection with Explainable AI
    Designed a Temporal-Aware 3D CNN using fMRI scans with Grad-CAM interpretability
    Slide

  • LibraMate: A Library Assistant Chatbot
    Built a GPT-4-powered chatbot using Streamlit and MySQL to assist library visitors
    Report

  • College Student Mental Health Prediction
    Compared ML models for early detection of mental health issues in students
    Slides

Awards and Honors

  • 🥇 1st Place – Health Informatics and Data Science Day, UNT (2024)
    Poster: LLM-based Counterspeech for Health Misinformation

Certifications

  • Deep Learning with PyTorch: Zero to GANs – Jovian
  • AI for Medical Diagnosis – DeepLearning.AI
  • Data Analyst Track – 365 Data Science

Academic Presentations

  • 🎤 ISCRAM 2025 Presenter – Fusion-based Crisis Communication
  • 🧠 UNT AI/CS Summer Research Poster – LLM Counterspeech for Misinformation
  • 🏆 UNT Health Informatics Poster Winner, 2024