avatar

Samarth Khanna

Ph.D. Student
Pennsylvania State University
samarth.khanna@psu.edu


About Me

I am pursuing my Ph.D. in Informatics at The Pennsylvania State University, advised by Professor Hadi Hosseini in the Foundations of Artificial Intelligence Lab (FAIR). My research investigates how large language models (LLMs) can serve as ethical decision-makers, with a focus on value alignment, procedural reasoning, and personalization. I study how well LLMs align with human moral and fairness judgments in collective decision-making domains such as resource allocation, kidney allocation, and matching markets; how reliably they can execute principled algorithms for aggregating preferences; and how they can be used to elicit individuals’ moral values from noisy responses and provide personalized ethical advice. Through this work, I aim to build a foundation for designing AI systems that are not only powerful but also ethically reliable and socially aligned.

Before Penn State, I worked as a Software Developer (June 2022 to July 2023) with Anchanto Pte Ltd., where I was responsible for writing the Back-end, Data Pipelines, and for building Machine Learning-based services such as Product Matching and Text Analysis. Prior to that, I completed my B.Tech. in Computer Science and Technology from IIEST, Shibpur in 2022.

On a personal note, I’m into reading, theater, and debating. I’ve also played a number of sports and I always enjoy playing anything new.

News

Publications

  1. Under review
    Preference Reasoning under Indeterminacy in Large Language Models
    Hadi Hosseini, Samarth Khanna, Xiyuan Wang
    (Alphabetical author ordering)

  2. AIES 2026
    The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions
    Hadi Hosseini, Samarth Khanna, Leona Pierce
    Ninth AAAI/ACM Conference on AI, Ethics, and Society
    PDF (Alphabetical author ordering)

  3. ACM EC 2026
    Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games
    Gonzalo Ballestero, Hadi Hosseini, Samarth Khanna, Ran I. Shorrer
    The Twenty-Seventh ACM Conference on Economics and Computation
    PDF (Alphabetical author ordering)

  4. Under review
    Fair Like Us? Auditing LLM Alignment in Resource Allocation
    Samarth Khanna, Sujoy Sikdar, Joshua Kavner, Hadi Hosseini, Qishen Han, Lirong Xia

  5. ACM FAccT 2026
    Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
    John P. Dickerson, Hadi Hosseini, Samarth Khanna, Leona Pierce
    The Ninth Annual ACM Conference on Fairness, Accountability, and Transparency
    PDF (Alphabetical author ordering)

  6. NeurIPS 2025
    Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
    Hadi Hosseini, Samarth Khanna, Ronak Singh
    The Thirty-Ninth Annual Conference on Neural Information Processing Systems
    PDF (Alphabetical author ordering)

  7. Under review
    Bridging Theory and Perception in Fair Division: A Study on Comparative and Fair Share Notions
    Hadi Hosseini, Joshua Kavner, Samarth Khanna, Sujoy Sikdar, Lirong Xia
    PDF (Alphabetical author ordering)

  8. NeurIPS 2025
    Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
    Hadi Hosseini, Samarth Khanna
    The Thirty-Ninth Annual Conference on Neural Information Processing Systems
    PDF BibTex (Alphabetical author ordering)

  9. MAISoN @ IJCAI 2023
    Link Prediction for Social Networks using Representation Learning and Heuristic-based Features
    Samarth Khanna, Sree Bhattacharyya, Sudipto Ghosh, Kushagra Agarwal, Asit Kumar Das
    9th International Workshop on Mining Actionable Insights from Social Networks (2023)
    PDF Code BibTex

  10. CIPR 2020
    A Comparative Study of Various Text Classification Methods
    Samarth Khanna, Bishnu Tiwari, Priyanka Das, Asit Kumar Das
    2nd International Conference on Computational Intelligence in Pattern Recognition
    PDF BibTex


Powered by Jekyll and Minimal Light theme.