Hello, my name is
Md. Shahidul Salim
PhD Student at University of Massachusetts Lowell, USA
🤗

My recent research focuses on LLM safety in the medical domain, GLP-1 drugs continuation detection, and reinforcement learning for readability control and for LLM guardrail breaking and defense. I also work on biomedical multilingual machine translation and electronic health record summarization using large language models (LLMs), while exploring uncertainty quantification in LLMs for medical settings.

🍀 If you are interested in collaboration or research opportunities, feel free to reach out!

Get in Touch Ask My Personal AI
Md. Shahidul Salim

Recent Updates

About Me

I am a Research Assistant at the University of Massachusetts Lowell, supervised by Dr. Hong Yu. I'm currently on study leave from my position as a Lecturer in the Department of Computer Science and Engineering at Khulna University of Engineering & Technology (KUET).

My research focuses on LLM safety in the medical domain, GLP-1 drugs continuation detection, reinforcement learning for readability control, and LLM guardrail breaking and defense, as well as biomedical multilingual machine translation and electronic health record summarization using LLMs. I also explore uncertainty quantification in medical LLMs, with the goal of building safer and more reliable language technologies for healthcare.

Academic & Work Timeline

Research Interests

LLM Safety in Medical Domain GLP-1 Drugs Continuation Detection Reinforcement Learning Readability Control LLM Guardrail Breaking & Defense Biomedical Machine Translation Clinical Summarization Uncertainty Quantification in LLMs Medical NLP LLM Fine-Tuning

Hobbies

Outside of research, I enjoy playing FIFA, traveling, and watching sci-fi and thriller movies. Some favorites include Interstellar, Dark, and Stranger Things.

Research Areas

Reinforcement Learning for Clinical NLP

Developing reinforcement-learning-based methods for readability control and for LLM guardrail breaking and defense.

Biomedical Translation & Summarization

Working on biomedical multilingual machine translation and electronic health record summarization using large language models (LLMs).

Uncertainty in Medical LLMs

Exploring uncertainty quantification in LLMs to improve reliability and decision support in medical settings.

🏆 Selected Research Papers

Natural Language Processing

    Machine Learning / Deep Learning

      📚 Other Publications

      Natural Language Processing

        Machine Learning / Deep Learning

          🔍 Under Review

            🔬 Ongoing Research

              💻 Projects

              My Skills

              AI & Machine Learning Expertise

              My technical expertise is primarily focused on Large Language Models (LLMs) and Machine Learning. I have extensive experience in building and optimizing AI workflows using PyTorch, VerL, Unsloth AI, vLLM, and Hugging Face Transformers. My work spans across Parameter-Efficient Fine-Tuning (PEFT), Reinforcement Learning, and Medical NLP, utilizing frameworks like LangChain, LlamaIndex, and Gradio to build intelligent applications.

              Beyond AI, I am proficient in Python and C/C++, and well-versed in data and deployment tools including Docker, FastAPI, FAISS/Chroma, Weights & Biases, Git, and Linux.

              Detailed Experience
              PyTorch VerL Unsloth AI vLLM Hugging Face Transformers LangChain LlamaIndex PEFT Reinforcement Learning Medical NLP Gradio FAISS/Chroma Weights & Biases Python C/C++ FastAPI Docker Linux Git NumPy pandas LaTeX HTML/CSS

              Contact Me

              Email

              mdshahidul_salim@student.uml.edu

              shahidulshakib034@gmail.com

              Address

              132 University Ave, Lowell, MA, USA

              Social Media