Het Shah

About Me

Hi! I am Het, a recent Computer Science graduate from IIIT Delhi. I have experience in working on projects around Natural Language Processing (NLP), Deep Learning (DL) and Reinforcement Learning (RL). I have done various internships and also published research papers at top venues like ACL, AAAI. I am open to discussing about new job/research opportunities around ML, NLP, DL and RL. Please feel free to contact me at het.shah25052004@gmail.com.

Research Interests

My research interests include but are not limited to Natural Language Processing, Large Language Models, Knowledge Graphs, Agentic AI, Retrieval Augmented Generation, Deep Learning, Generative AI, Reinforcement Learning. In Natural Language Processing, I am interested in working around LLM applications, agentic AI, and core LLM optimization problems. In Reinforcement Learning, I am interested in working on LLM post training using reinforcement learning. I have published a research paper on training generalist reasoning models using a novel Group Relative Policy Optimization (GRPO) based approach at AAAI 2026 Plan Bridge FM workshop. I have worked as an Undergraduate Researcher at IIIT Delhi in Flame.nlp Research Lab under Dr. Md. Shad Akhtar (work published at ACL 2026 Main Conference(oral presentation)). Along with this, I have had the opportunity to do Research Internships at AI Institute of University of South Carolina (AIISC) under the guidance of Dr. Amit Sheth (work published at AAAI 2026 Main Conference) and at IIT Patna under the guidance of Dr. Sriparna Saha.

Industry Experience

I have interned as a Machine Learning Scientist Intern at Wadhwani AI where I worked on improving domain specific models for question answering task using Retrieval Augmented Generation (RAG). I developed a special hierarchical chunking technique which improved the retrieval and reranking results by 18% and 19% respectively on recall@k metrics. Along with this, I deployed the end-to-end RAG pipeline (retrieval, reranker, and final answer generation models) for commercial use.

Publications

• Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation
  Abdullah Mazhar, Het Riteshkumar Shah, Aseem Srivastava, Smriti Joshi, Md Shad Akhtar
  Accepted at ACL 2026 Oral Presentation
• PAL: Personal Adaptive Learner
  Megha Chakraborty, Darssan L. Eswaramoorthi, Madhur Thareja, Het Riteshkumar Shah, Finlay Palmer, Aryaman Bahl, Michelle A Ihetu, Amit Sheth
  Accepted at AAAI 2026.
  
• Rethinking Reward Models! A Conceptual Framework for Enhancing LLM Reasoning through Intrinsic Traits
  Het Riteshkumar Shah, Megha Sundriyal
  Accepted at AAAI 2026 PLAN-FM Bridge Workshop.
  
• Keep it SIMPLE, Bing! Leveraging Contrastive Regularization for Multimodal Sarcasm Explanation
  Het Riteshkumar Shah, Palaash Goel, Md. Shad Akhtar
  Under Review
  
• CANDI – Contextual Alignment for Niche Domains Question Answering
  Megha Chakraborty, Darssan L. Eswaramoorthi, Het Riteshkumar Shah, Madhur Thareja, Michelle A Ihetu, Harshul Raj Surana, Kaushik Roy, Amit Sheth
  Under Review