Manav Chaudhary

Namaste! I am currently working at SentiSum, building ML-powered intelligent systems to improve customer experience analytics — leveraging Voice of Customer data to help brands identify hidden friction, resolve barrier issues, and recover potential revenue loss.

I recently completed my dual degree (B.Tech + M.S.) in Computer Science and Engineering from IIIT Hyderabad, where I also worked as a Research Assistant at the Information Retrieval and Extraction Lab (iREL), advised by Dr. Vasudeva Varma. My research has spanned reference-free evaluation, LLM robustness, code generation, healthcare, education, and mental health AI — leading to publications in ACL, ICSE, and Nature Scientific Reports.

My core research interests lie in LLM evaluation and robustness, machine-generated text detection, explainable AI and AI for healthcare and education. I believe that bridging strong engineering foundations with user-facing impact is how AI best delivers on its promise — and that’s what I strive to build in every endeavour.

news

Jun 30, 2025	Happy to share that I’ve successfully defended my thesis titled “You Can (Not) Trust: Reliability and Robustness of LLMs as Human-Like Annotators and Judges.” This work explores critical questions about the reliability, robustness, and alignment of Large Language Models (LLMs) when used for annotation and evaluation tasks in NLP. It investigates the indistinguishability of LLM-generated and human annotations, the alignment and reliability of LLMs as subjective judges of language quality, and their susceptibility to misinformation in evaluation settings. Two papers from this work have been accepted, and we’re actively working on future directions. I’m deeply grateful to my advisor Vasudeva Varma, reviewers Vikram Pudi and Asif Ekbal, my collaborators, and the iREL lab at IIIT Hyderabad. Joining this lab has truly been a life-changing decision, and I’m thankful for the support and freedom I’ve received throughout this journey.
May 16, 2025	Thrilled to share that our paper, “Screening of Oral Potentially Malignant Disorders and Oral Cancer Using Deep Learning Models,” has been accepted in Scientific Reports, a Nature Portfolio journal (2025). This research was part of my internship at the Applied AI Research Centre (INAI, IIIT Hyderabad), a collaborative initiative by IIIT-H, Intel, the Government of Telangana, and PHFI. We applied AI to improve early detection of oral cancer through deep learning and image analysis. Grateful to be part of impactful healthcare research using AI.

Jun 30, 2025

Happy to share that I’ve successfully defended my thesis titled “You Can (Not) Trust: Reliability and Robustness of LLMs as Human-Like Annotators and Judges.” This work explores critical questions about the reliability, robustness, and alignment of Large Language Models (LLMs) when used for annotation and evaluation tasks in NLP. It investigates the indistinguishability of LLM-generated and human annotations, the alignment and reliability of LLMs as subjective judges of language quality, and their susceptibility to misinformation in evaluation settings. Two papers from this work have been accepted, and we’re actively working on future directions. I’m deeply grateful to my advisor Vasudeva Varma, reviewers Vikram Pudi and Asif Ekbal, my collaborators, and the iREL lab at IIIT Hyderabad. Joining this lab has truly been a life-changing decision, and I’m thankful for the support and freedom I’ve received throughout this journey.

May 16, 2025

Thrilled to share that our paper, “Screening of Oral Potentially Malignant Disorders and Oral Cancer Using Deep Learning Models,” has been accepted in Scientific Reports, a Nature Portfolio journal (2025). This research was part of my internship at the Applied AI Research Centre (INAI, IIIT Hyderabad), a collaborative initiative by IIIT-H, Intel, the Government of Telangana, and PHFI. We applied AI to improve early detection of oral cancer through deep learning and image analysis. Grateful to be part of impactful healthcare research using AI.