I am a PhD student in Computer Science at Tufts University where I work under the supervision of Dr. Vasanth Sarathy. I am generally interested in Natural Language Processing, and its intersection with social sciences and argumentation. I am also interested in fairness in NLP systems and how we can both assess and mitigate biases in Large Language Models.

Prior to Tufts, I was a master’s student in computer Science at Worcester Polytechnic Institute where I worked with Dr. Rose Bohrer on Linear Logic Programming and its applications to exploit detection in Software Systems.

I love talking about all-things NLP (also video games, fantasy and sci-fi books, and sports) and I am open to collaboration. Feel free to drop me an email.

News

Happy to announce that we have one paper accepted for LREC 2026:

• Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation.

Two papers accepted for AAAI 2026:

• IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection, accepted for Demonstration Track.

• Where Norms and References Collide: Evaluating LLMs on Normative Reasoning, accepted for the main technical track.

I will be serving as a program committee member for AAAI 2026.

I will be serving as a reviewer for AIES 2025.

I will be serving as a reviewer for AISTATS 2025 in the Natural Language Processing (NLP) track.

I will be serving as a reviewer for ICLR 2025 in the Natural Language Processing (NLP) track.

I will be attending EMNLP 2024 to present our latest paper titled ““Let’s Argue Both Sides”: Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities” at the Workshop on Customizable NLP.

Publications

IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection (Kaveh Eskandari Miandoab, Katharine Kowalyshyn, Kabir Pamnani, Anesu Gavhera, Vasanth Sarathy and Matthias Scheutz)

Where Norms and References Collide: Evaluating LLMs on Normative Reasoning (Mitchell Abrams, Kaveh Eskandari Miandoab, Felix Gervits, Vasanth Sarathy and Matthias Scheutz)

Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation (Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni, Gene Louis Kim, Vasanth Sarathy and Ninareh Mehrabi)

Noise Injection Systemically Degrades Large Language Model Safety Guardrails (Prithviraj Singh Shahani, Kaveh Eskandari Miandoab and Matthias Scheutz)

“Let’s Argue Both Sides”: Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities (Kaveh Eskandari Miandoab and Vasanth Sarathy)

DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias (Mahdi Zakizadeh, Kaveh Eskandari Miandoab and Mohammad Taher Pilehvar)