Maribeth Rauh, John Mellor, Jonathan Uesato, Po-Sen Huang, Johannes Welbl, Laura Weidinger, Sumanth Dathathri, Amelia Glaese, Geoffrey Irving, Iason Gabriel, William Isaac 0001, Lisa Anne Hendricks. Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]
@inproceedings{RauhMUHWWDGIGIH22, title = {Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models}, author = {Maribeth Rauh and John Mellor and Jonathan Uesato and Po-Sen Huang and Johannes Welbl and Laura Weidinger and Sumanth Dathathri and Amelia Glaese and Geoffrey Irving and Iason Gabriel and William Isaac 0001 and Lisa Anne Hendricks}, year = {2022}, url = {http://papers.nips.cc/paper_files/paper/2022/hash/9ca22870ae0ba55ee50ce3e2d269e5de-Abstract-Datasets_and_Benchmarks.html}, researchr = {https://researchr.org/publication/RauhMUHWWDGIGIH22}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, isbn = {9781713871088}, }