Publications

  1. Natural Language Reinforcement Learning
    Xidong Feng, B. Liu, Y. Song, and 7 more authors
    Nov 2024
    Accepted
    arXiv
  2. TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
    Girish A. Koushik, Helen Treharne, and Diptesh Kanojia
    In AAAI-ICWSM 2027, Jan 2026
    Accepted
  3. Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine Translation
    A. Sindhujan, Girish A. Koushik, S. Qian, and 2 more authors
    Cambridge NLP Journal, Dec 2025
    Accepted
  4. The Mind’s Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
    Girish A. Koushik, Fatemeh Nazarieh, K. Birch, and 2 more authors
    In GenProCC Workshop at NeurIPS 2025, Aug 2025
    Accepted
    arXiv Code
  5. Cyberbullying Detection via Aggression-Enhanced Prompting
    A. Saeid, A. Sabu, Girish A. Koushik, and 2 more authors
    In Recent Advances in Natural Language Processing, Aug 2025
    arXiv
  6. TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection
    Girish A. Koushik, Helen Treharne, A. Joshi, and 1 more author
    arXiv preprint arXiv:2504.17902, Apr 2025
    Accepted to the AISI Track at AAAI 2026
    arXiv Code
  7. Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
    Girish A. Koushik, Diptesh Kanojia, and Helen Treharne
    arXiv preprint arXiv:2502.07138, Dec 2024
    Accepted to the MM4SG Workshop at The Web Conference 2025
    arXiv Code