Arka Dutta
Orcid: 0009-0009-1649-1848Affiliations:
- Rochester Institute of Technology, Rochester, NY, USA
According to our database1,
Arka Dutta authored at least 9 papers
between 2023 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
Online presence:
-
on github.com
On csauthors.net:
Bibliography
2026
What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency in Closed Domains Via Adversarial Nudge.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
How Can You Tell if Your Large Language Model Could Be a Closet Antisemite? An Explainability-Based Audit Framework for Implicit Bias.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026
2025
What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge.
CoRR, November, 2025
Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups.
CoRR, April, 2025
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025
All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract).
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025
2024
Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024
2023
Classification of Cricket Shots from Cricket Videos Using Self-attention Infused CNN-RNN (SAICNN-RNN).
Proceedings of the Computational Intelligence in Communications and Business Analytics, 2023