Publications
* denotes equal contribution as co-first authors.
- What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge. (ACL Main 2026)
- Auditing LLM Response to Harmful Stereotypes Targeting Mental Health Groups (ACL Findings 2026)
- 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)
- All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract) (AAAI 2025).
- Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny. (IJCAI 2024).
- Classification of Cricket Shots from Cricket Videos Using Self-attention Infused CNN-RNN (SAICNN-RNN). (CICBA 2023). [Springer Link]
Manuscripts
- Race in the Record: Measuring Racial Signal and Model Inference in Police Arrest Narratives (Accepted, To appear)
- Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation (Accepted, To appear)
- SPaRTA: Spatial Reasoning in Text-to-SQL for Omics Analysis (In Review - arxiv version)
- Investigating Intersectionality in Large Language Models. (In Review - arxiv version)
- Counterbalancing Hate with Positivity: A Survey of Counterspeech.