Publications

* denotes equal contribution as co-first authors. † work done during internship at Amazon.

• Race in the Record: Measuring Racial Signal and Model Inference in Police Arrest Narratives

  Arka Dutta, Ted Forsyth, O. Nicholas Robertson, Ashiqur R. KhudaBukhsh

  EMNLP 2026 · Main Award nomination Paper coming soon

• Physiognomy Revisited: How Vision–Language Models Encode Sensitive Attributes Through Image Transformation

  Soumyajit Datta, Arka Dutta, Ashiqur R. KhudaBukhsh

  EMNLP 2026 · Main Paper coming soon

• Are LLM Shopping Agents Behaviorally Distinguishable from Human Shoppers? A Session-Level Study †

  Arka Dutta, Virinchi Roy Surabhi, Jiayue Tong, Dihan Dai, Amila Weerasinghe, Olcay Boz

  REALM @ EMNLP 2026 · Workshop Paper coming soon
• 

  Truths, Lies, and Nudge — HAUNT: A Framework to Probe LLMs' Self-consistency in Closed Domains via Adversarial Nudge

  Arka Dutta, Sujan Dutta, Rijul Magu, Soumyajit Datta, Munmun De Choudhury, Ashiqur R. KhudaBukhsh

  ACL 2026 · Main ACL Anthology
• 

  Auditing LLM Response to Harmful Stereotypes Targeting Mental Health Groups

  Arka Dutta, Rijul Magu, Sean Kim, Seohee Yoon, Munmun De Choudhury, Ashiqur R. KhudaBukhsh

  ACL 2026 · Findings ACL Anthology
• 

  How Can You Tell if Your Large Language Model Could Be a Closet Antisemite? A Framework to Bias-Audit Large Language Models

  Arka Dutta, Reza Fayyazi, Shanchieh Yang, Ashiqur R. KhudaBukhsh

  AAAI 2026 Proceedings
• 

  A Large-Scale Social-Web Audit of AI-Generated-Text Detection Systems

  Arka Dutta*, Utkarshani Jaimini*, Utkarsh Bhatt, Sara Shree Muthuselvam, Amitava Das, Ashiqur R. KhudaBukhsh

  ICWSM 2026 Proceedings
• 

  Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups

  Rijul Magu, Arka Dutta, Sean Kim, Ashiqur R. KhudaBukhsh, Munmun De Choudhury

  COLM 2025 PDF
• 

  Towards a Bipartisan Understanding of Peace and Vicarious Interactions

  Arka Dutta*, Syed M. Sualeh Ali*, Usman Naseem, Ashiqur R. KhudaBukhsh

  IJCAI 2025 Proceedings
• 

  All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract)

  Arka Dutta, Aman Priyanshu, Ashiqur R. KhudaBukhsh

  AAAI 2025 Proceedings
• 

  Down the Toxicity Rabbit Hole: A Framework to Bias-Audit LLMs with Key Emphasis on Racism, Antisemitism, and Misogyny

  Arka Dutta*, Adel Khorramrouz*, Sujan Dutta, Ashiqur R. KhudaBukhsh

  IJCAI 2024 Proceedings
• 

  Classification of Cricket Shots from Cricket Videos Using Self-Attention-Infused CNN-RNN (SAICNN-RNN)

  Arka Dutta, Abhishek Baral, Sayan Kundu, Sayantan Biswas, Kousik Dasgupta, Hasanujjaman

  CICBA 2023 Springer

No publications match this filter.

Manuscripts

• When Does Iterative LLM Rewriting Stop Helping? Quality, Semantic Drift, and Dynamics in Scientific-Prose Revision

  Abhidipto Chakraborty*, Arka Dutta*, Soumyajit Datta, Ashiqur R. KhudaBukhsh

  In review

• SPaRTA: Spatial Reasoning in Text-to-SQL for Omics Analysis

  Arka Dutta, Souvik Ghosh, Kenneth Prado, Ashiqur R. KhudaBukhsh, Hirak Sarkar

  In review

• HAUNT Cultural Atlas: Where LLM Cultural Knowledge Runs Thin

  Arka Dutta, Tanuja Ganu, Ashiqur R. KhudaBukhsh

  In review

• Investigating Intersectionality in Large Language Models

  Soumyajit Datta, Arka Dutta, Dhruv Vaidh, Sujan Dutta, Ashiqur R. KhudaBukhsh

  In review

Academic Service

• Reviewer / PC IJCAI 2025IJCAI 2026AAAI 2026NeurIPS 2026ICWSM 2026WWW 2025

Mentorship

I mentored three undergraduate researchers at RIT through the NSF REU 2026 program, advising them from problem formulation through experiments and writing. The work led to two research projects currently under review at top venues.

• Abhidipto Chakraborty — The University of Texas at Austin
• Stephanie Birkelbach — Texas A&M University
• Jollen Dai — University of California, Los Angeles