Hello! I’m Arka, a PhD student in Computing and Information Sciences at Rochester Institute of Technology, advised by Prof. Ashiqur R. KhudaBukhsh at the Social Insight Lab. My research lies at the intersection of Natural Language Processing and Computational Social Science, focusing on creating fair, responsible, and equitable Generative AI systems. My work has been featured at leading conferences (AAAI, IJCAI) and recognized globally by media outlets such as CNN, WIRED, and Montreal AI Ethics Magazine. Passionate about Maths and problem solving, I actively integrate advanced mathematical concepts from combinatorics, optimization, and probability theory to enhance the robustness and fairness of AI models.
Our work in News
- Featured on Good Morning America — coverage of our research revealing how AI chatbots can generate hateful online content. Read on GMA
- Covered by ABC News — highlighting our findings on how generative AI systems produce hate speech and bias. Read on ABC News
- Featured on CNN — our study on antisemitism in large language models and the hidden biases shaping AI responses. Read on CNN
- Featured in WIRED — coverage of our work auditing political and social bias in large language models. Read on WIRED
- RIT News — spotlighting our team’s publication on generative AI and harmful content generation. Read on RIT News
- Featured by Montreal AI Ethics Institute — analysis of our paper “Down the Toxicity Rabbit Hole” and its insights into LLM guardrails. Read on MAIEI
Selected Publications
- How Can You Tell if Your Large Language Model Could Be a Closet Antisemite? A Framework to Bias Audit Large Language Models. (AAAI 2026)
- A Large Scale Social Web Audit of AI Generated Text Detection Systems. (ICWSM 2026)
- Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups. (COLM 2025)
- Towards a Bipartisan Understanding of Peace and Vicarious Interactions. (IJCAI 2025)
- Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny. (IJCAI 2024).
Skills
- Machine Learning (ML), Artificial Intelligence (AI), Natural Language Processing (NLP), Large Language Model (LLM), Explainable AI (XAI), Reinforcement Learning with Human Feedback (RLHF), Deep Learning, Responsible AI, Optimization, Statistical Inference, Quantitative Finance, Quantitative Research, Predictive Modeling, Data Visualization.
- Python, C/C++, MATLAB, SQL, Transformers, PyTorch, TensorFlow, NumPy, Pandas, NLTK, Spacy, HuggingFace, SHAP
Selected Achievements
- RIT Language Science Student Excellence Award (2024): One of the two recipients of the award among 1000+ students university-wide in 2024; for the research in responsible AI and NLP systems.
- Common Admission Test (CAT, 2022): Achieved 98.97 percentile in CAT 2022 (among 100k+ candidates), securing admission to the PGP at Indian Institute of Management Indore (IIMI), a premier B-school (top 100 globally, Financial Times).
- Regional Mathematics Olympiad (2018): Qualified for prestigious RMO, WB; demonstrating advanced level aptitude in Discrete Mathematics, Combinatorics, Number Theory, Algebra, Geometry, and Optimization.
- Jagadish Bose National Science Talent Scholarship (2017): Awarded prestigious JBNSTS scholarship for excellence in science