Akash Kundu

Papers, and (eventually) essays.

Every paper, in one place. I also keep meaning to write essays. This is the page they'll go on when I do.

Papers

h-index 5 · 233 citations Google Scholar →

  1. DarkBench: Benchmarking Dark Patterns in Large Language Models

    Equal-first author

    Esben Kran, Hieu Minh Nguyen, Akash Kundu, Sami Jawhar, Jinsuk Park, and Mateusz Maria Jurewicz

    ICLR 2025 · preliminary version at AAAI 2025 DATASAFE · Oral · top 1.8%

  2. Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation

    First author

    Akash Kundu, Emanuel Tewolde, Ratip Emin Berker, Samuel F. Brown, and Vincent Conitzer

    AI4Good Workshop, ICML 2026 · under review at NeurIPS 2026 · Accepted

  3. MMTEB: Massive Multilingual Text Embedding Benchmark

    Kenneth Enevoldsen, Isaac Chung, Imene Kerboua, and many others, including Akash Kundu

    ICLR 2025

  4. Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

    Chris Smith, Marwa Abdulhai, Mark Diaz, and others, including Akash Kundu

    NeurIPS 2025 Datasets & Benchmarks

  5. Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects

    Reva Schwartz, Rumman Chowdhury, Akash Kundu, Heather Frase, and others

    arXiv 2505.18893 · under review at NeurIPS 2025

  6. Red Teaming for Trust: Evaluating Multicultural and Multilingual AI Systems in Asia-Pacific

    First author

    Akash Kundu, Adrianna Tan, Theodora Skeadas, Rumman Chowdhury, and Sarah Amos

    ICLR 2025 Workshop on Building Trust in Language Models and Applications

  7. AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology

    First author

    Akash Kundu and Rishika Goswami

    IJCNLP-AACL 2025 Student Research Workshop

  8. Ask What Your Country Can Do For You: Towards a Public Red Teaming Model

    Wm. Matthew Kennedy, Rumman Chowdhury, Reva Schwartz, and others, including Akash Kundu

    CAMLIS Red Workshop

  9. An Approach to Detect and Classify Potentially Suspicious Activity from Real-Time Log Data using Anomaly Detection Methods

    Arnab Sengupta, Akash Kundu, and Aishi Mukhopadhyay

    INOCON 2024 (IEEE)

Essays

I used to write a lot, then I stopped. I want to start again. No schedule, no newsletter. Just dropping things here when I have something to say.

Nothing here yet. I'll get to it.