Neeladri Bhuiya

About Me

I am a master’s student at the Manning College of Information and Computer Sciences at UMass Amherst, broadly interested in AI Safety, representation learning, and LLM evaluation.

My master’s thesis, supervised by Dr. Haw Shiuan Chang and Dr. Andrew McCallum, proposes modeling LLM prompts as box embeddings, axis-aligned hyperrectangles in high-dimensional space. Unlike vector embeddings, which capture only topical similarity, box embeddings jointly represent both semantic relevance and specificity, better preserving prompt structure and revealing improved performance and interesting scaling behaviors. The paper is available here: Prompt2Box.

During my undergrad, I worked with Dr. Viktor Schlegel and Dr. Stefan Winkler on multi-hop reasoning in LLMs. I designed an adversarial attack using dependency parsing to expose systematic shortcutting behavior during inference, finding that LLMs exploit such shortcuts more covertly than smaller models like BERT and Longformer. This work was published at EMNLP 2024.

News

• January 2026 — My work at A10 Networks, PLAGUE was accepted into ICLR 2026!
• May 2025 — I will spend my summer interning at A10 Networks in San Jose as an AI Safety Intern!
• November 2024 — Presented “Seemingly Plausible Distractors” at EMNLP in Miami!
• September 2024 — Started my master’s in Computer Science at UMASS!
• May 2024 — Graduated with a Bachelor’s in Computer Science from NUS!