Papers

A list of my publications.

View my Google Scholar Page

2026

  1. ICML
    When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
    Mubashara Akhtar, Anka Reuel, Prajna Soni, Sanchit Ahuja, and 33 more authors
    International Conference on Machine Learning, Jul 2026
  2. ICML
    Position: Agentic Systems Should be General
    Elron Bandel, Asaf Yehudai, Alexandre Lacoste, Avijit Ghosh, and 4 more authors
    International Conference on Machine Learning, Jul 2026
  3. ICML
    Who Evaluates AI’s Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
    Anka Reuel, Avijit Ghosh, Jenny Chim, Andrew Tran, and 31 more authors
    International Conference on Machine Learning, Jul 2026
  4. EvalEval
    Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture
    Aidan Kierans, Ritam Dutt, Kaley Rittichier, Shiri Dori-Hacohen, and 1 more author
    EvalEval Workshop at the Annual Meeting of the Association for Computational Linguistics, Jul 2026
  5. TAIGR
    Intelligence Is Not the Bottleneck: Structural Barriers to Automating Alignment Research
    Aidan Kierans, Stephen Casper, and Avijit Ghosh
    TAIGR Workshop at the International Conference on Machine Learning, Jul 2026
  6. FAccT
    What if AI Systems Weren’t Chatbots?
    Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam, and Avijit Ghosh
    ACM Conference on Fairness, Accountability, and Transparency, Jun 2026
  7. TMLR
    Open Technical Problems in Open-Weight AI Model Risk Management
    Stephen Casper, Kyle O’Brien, Shayne Longpre, Elizabeth Seger, and 18 more authors
    Transactions on Machine Learning Research, Mar 2026
  8. Patterns
    AI for Scientific Discovery is a Social Problem
    Georgia Channing, and Avijit Ghosh
    Patterns, Mar 2026

2025

  1. Book Chapter
    Evaluating the social impact of generative ai systems in systems and society
    Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, and 27 more authors
    Dec 2025
  2. Preprint
    Economies of Open Intelligence: Tracing Power & Participation in the Model Ecosystem
    Shayne Longpre, Christopher Akiki, Campbell Lund, Atharva Kulkarni, and 5 more authors
    arXiv preprint arXiv:2512.03073, Dec 2025
  3. AIES
    Documenting Patterns of Exoticism of Marginalized Populations within Text-to-Image Generators
    Sourojit Ghosh, Sanjana Gautam, Pranav Venkit, and Avijit Ghosh
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, Oct 2025
  4. Preprint
    Position: Aligning AI Requires Automating Reasoning Norms
    Aidan Kierans, Avijit Ghosh, and Shiri Dori-Hacohen
    Sep 2025
    Preprint on SSRN
  5. ICML
    Stop treating ’AGI’ as the north-star goal of AI research
    Borhane Blili-Hamelin, Christopher Graziul, Leif Hancox-Li, Hananel Hazan, and 12 more authors
    International Conference on Machine Learning, Jul 2025
  6. ICML
    In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
    Shayne Longpre, Kevin Klyman, Ruth E. Appel, Sayash Kapoor, and 30 more authors
    International Conference on Machine Learning, Jul 2025
  7. FAccT
    "It’s not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services
    Shira Michel, Sufi Kaur, Sarah Elizabeth Gillespie, Jeffrey Gleason, and 2 more authors
    ACM Conference on Fairness, Accountability, and Transparency, Jun 2025
  8. Preprint
    A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets
    Ryan Lagasse, Aidan Kierans, Avijit Ghosh, and Shiri Dori-Hacohen
    arXiv preprint arXiv:2505.06150, May 2025
  9. Preprint
    Catastrophic Liability: Managing Systemic Risks in Frontier AI Development
    Aidan Kierans, Kaley Rittichier, Utku Sonsayar, and Avijit Ghosh
    arXiv preprint arXiv:2505.00616, May 2025
  10. CHI
    Protecting Human Cognition in the Age of AI
    Anjali Singh, Karan Taneja, Zhitong Guan, and Avijit Ghosh
    Tools for Thought Workshop at Conference on Human Factors in Computing Systems, Apr 2025
  11. Preprint
    Fully Autonomous AI Agents Should Not be Developed
    Margaret Mitchell, Avijit Ghosh, Alexandra Sasha Luccioni, and Giada Pistilli
    arXiv preprint arXiv:2502.02649, Feb 2025
  12. AAAI
    Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment
    Aidan Kierans, Avijit Ghosh, Hananel Hazan, and Shiri Dori-Hacohen
    Thirty-Ninth AAAI Conference on Artificial Intelligence, Feb 2025
  13. IAAI
    To Err is AI: A Case Study Informing LLM Flaw Reporting Practices
    Sean McGregor, Allyson Ettinger, Nick Judd, Paul Albee, and 9 more authors
    Thirty-Seventh Annual Conference on Innovative Applications of Artificial Intelligence - AAAI Workshop, Feb 2025

2024

  1. FAccTRec
    Reducing Population-level Inequality Can Improve Demographic Group Fairness: a Twitter Case Study
    Avijit Ghosh, Tomo Lazovich, Kristian Lum, and Christo Wilson
    Workshop on Responsible Recommendation - RecSys Workshop, Oct 2024
  2. AIES
    Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
    Sven Cattell, Avijit Ghosh, and Lucie-Aimée Kaffee
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, Oct 2024
  3. WWW
    Perceptions in pixels: analyzing perceived gender and skin tone in real-world image search results
    Jeffrey Gleason, Avijit Ghosh, and Christo Wilson
    Proceedings of the International World Wide Web Conference, May 2024

2023

  1. AIES
    When Fair Classification Meets Noisy Protected Attributes
    Avijit Ghosh, Pablo Kvitca, and Christo Wilson
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2023
  2. AIES
    Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
    Organizers QueerInAI, Nathan Dennler, Anaelia Ovalle, Ashwin Singh, and 10 more authors
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2023
  3. FAccT
    Queer In AI: A Case Study in Community-Led Participatory AI
    Organizers Of QueerInAI, Anaelia Ovalle, Arjun Subramonian, Ashwin Singh, and 46 more authors
    ACM Conference on Fairness, Accountability, and Transparency, 2023

2022

  1. HEGM
    Can There be Art Without an Artist?
    Avijit Ghosh, and Genoveva Fossas
    NeurIPS Workshop on Human Evaluation of Generative Models, 2022
  2. AIES
    Faircanary: Rapid continuous explainable fairness
    Avijit Ghosh, Aalok Shanbhag, and Christo Wilson
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2022
  3. AIES
    Algorithms that "Don’t See Color": Measuring Biases in Lookalike and Special Ad Audiences
    Piotr Sapiezynski, Avijit Ghosh, Levi Kaplan, Aaron Rieke, and 1 more author
    Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2022
  4. FAccT
    Subverting Fair Image Search with Generative Adversarial Perturbations
    Avijit Ghosh, Matthew Jagielski, and Christo Wilson
    ACM Conference on Fairness, Accountability, and Transparency, 2022

2021

  1. SIGIR
    When Fair Ranking Meets Uncertain Inference
    Avijit Ghosh, Ritam Dutt, and Christo Wilson
    Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, 2021
  2. FAccT
    Building and auditing fair algorithms: A case study in candidate screening
    Christo Wilson, Avijit Ghosh, Shan Jiang, Alan Mislove, and 4 more authors
    Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, 2021
  3. AIDBEI
    Characterizing Intersectional Group Fairness with Worst-Case Comparisons
    Avijit Ghosh, Lea Genuit, and Mary Reagan
    Workshop on Diversity in Artificial Intelligence: Diversity, Belonging, Equity, and Inclusion (AIDBEI) at AAAI, 2021
  4. AAA
    Connectedness of Markets with Heterogeneous Agents and the Information Cascades
    Avijit Ghosh, Aditya Chourasiya, Lakshay Bansal, and Abhijeet Chandra
    Applied Advanced Analytics: 6th IIMA International Conference on Advanced Data Analysis, Business Analytics and Intelligence, 2021
  5. Preprint
    Unified shapley framework to explain prediction drift
    Aalok Shanbhag, Avijit Ghosh, and Josh Rubin
    arXiv preprint arXiv:2102.07862, 2021

2019

  1. ConPro
    Analyzing Political Advertisers’ Use of Facebook’s Targeting Features
    Avijit Ghosh, Giri Venkatadri, and Alan Mislove
    Workshop on Technology and Consumer Protection, 2019
  2. ECIR
    Public sphere 2.0: Targeted commenting in online news media
    Ankan Mullick, Sayan Ghosh, Ritam Dutt, Avijit Ghosh, and 1 more author
    Advances in Information Retrieval: 41st European Conference on IR Research (ECIR), 2019

2018

  1. SMERP
    SAVITR: A System for Real-time Location Extraction from Microblogs during Emergencies
    Ritam Dutt, Kaustubh Hiware, Avijit Ghosh, and Rameshwar Bhaskaran
    WWW’18 Workshop on Exploitation of Social Media for Emergency Relief and Preparedness, 2018

2016

  1. WITS
    WebSelect: A Research Prototype for Optimizing Ad Exposures based on Network Structure
    Avijit Ghosh, Agam Gupta, Divya Sharma, and Uttam Sarkar
    Workshop on Information Technology and Sciences (WITS), 2016
Email Options