Search results

  • Full text

  • Document type

    • Publication year

  • Organisation

Results: 13
Number of items: 13
  • Open Access
    Chintam, A., Beloch, R., Zuidema, W., Hanna, M., & van der Wal, O. (2023). Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model. In Y. Belinkov, S. Hao, J. Jumelet, N. Kim, A. McCarthy, & H. Mohebbi (Eds.), BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP: Proceedings of the Sixth Workshop : EMNLP 2023 : December 7, 2023 (pp. 379-394). The Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.blackboxnlp-1.29
  • Open Access
    Hanna, M., Liu, O., & Variengien, A. (2023). How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, & S. Levine (Eds.), 37th Conference on Neural Information Processing Systems (NeurIPS 2023): 10-16 December 2023, New Orleans, Louisana, USA (pp. 76033-76060). (Advances in Neural Information Processing Systems; Vol. 36). Neural Information Processing Systems Foundation. https://doi.org/10.52202/075280-3322
  • Open Access
    Jumelet, J., Hanna, M., de Heer Kloots, M., Langedijk, A., Pouw, C., & van der Wal, O. (2023). ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation. In A. Warstadt, A. Mueller, L. Choshen, E. Wilcox, C. Zhuang, J. Ciro, R. Mosquera, B. Paranjabe, A. Williams, T. Linzen, & R. Cotterell (Eds.), Findings of the BabyLM Challenge: Sample-efficient pretraining on developmentally plausible corpora (pp. 74-85). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.conll-babylm.6
Page 2 of 2