| Ex machina: Personal attacks seen at scale E Wulczyn, N Thain, L Dixon Proceedings of the 26th international conference on world wide web, 1391-1399, 2017 | 914 | 2017 |
| Measuring and mitigating unintended bias in text classification L Dixon, J Li, J Sorensen, N Thain, L Vasserman Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, 67-73, 2018 | 833 | 2018 |
| Nuanced metrics for measuring unintended bias with real data for text classification D Borkan, L Dixon, J Sorensen, N Thain, L Vasserman Companion proceedings of the 2019 world wide web conference, 491-500, 2019 | 457 | 2019 |
| Gemma: Open models based on gemini research and technology G Team, T Mesnard, C Hardin, R Dadashi, S Bhupatiraju, S Pathak, ... arXiv preprint arXiv:2403.08295, 2024 | 440 | 2024 |
| Fairness without demographics through adversarially reweighted learning P Lahoti, A Beutel, J Chen, K Lee, F Prost, N Thain, X Wang, E Chi Advances in neural information processing systems 33, 728-740, 2020 | 340 | 2020 |
| Conversations gone awry: Detecting early signs of conversational failure J Zhang, JP Chang, C Danescu-Niculescu-Mizil, L Dixon, Y Hua, N Thain, ... arXiv preprint arXiv:1805.05345, 2018 | 220 | 2018 |
| Toxicity detection: Does context really matter? J Pavlopoulos, J Sorensen, L Dixon, N Thain, I Androutsopoulos arXiv preprint arXiv:2006.00998, 2020 | 156 | 2020 |
| Plex: Towards reliability using pretrained large model extensions D Tran, J Liu, MW Dusenberry, D Phan, M Collier, J Ren, K Han, Z Wang, ... arXiv preprint arXiv:2207.07411, 2022 | 109 | 2022 |
| Crowdsourcing subjective tasks: the case study of understanding toxicity in online discussions L Aroyo, L Dixon, N Thain, O Redfield, R Rosen Companion proceedings of the 2019 world wide web conference, 1100-1105, 2019 | 104 | 2019 |
| Debiasing embeddings for reduced gender bias in text classification F Prost, N Thain, T Bolukbasi arXiv preprint arXiv:1908.02810, 2019 | 79 | 2019 |
| Primes in certain arithmetic progressions R Murty, N Thain Functiones et Approximatio Commentarii Mathematici 35, 249-259, 2006 | 56 | 2006 |
| Convai at semeval-2019 task 6: Offensive language identification and categorization with perspective and bert J Pavlopoulos, N Thain, L Dixon, I Androutsopoulos Proceedings of the 13th international Workshop on Semantic Evaluation, 571-576, 2019 | 55 | 2019 |
| Six attributes of unhealthy conversation I Price, J Gifford-Moore, J Fleming, S Musker, M Roichman, G Sylvain, ... arXiv preprint arXiv:2010.07410, 2020 | 49 | 2020 |
| Measuring recommender system effects with simulated users S Yao, Y Halpern, N Thain, X Wang, K Lee, F Prost, EH Chi, J Chen, ... arXiv preprint arXiv:2101.04526, 2021 | 42 | 2021 |
| WikiConv: A corpus of the complete conversational history of a large online collaborative community Y Hua, C Danescu-Niculescu-Mizil, D Taraborelli, N Thain, J Sorensen, ... arXiv preprint arXiv:1810.13181, 2018 | 37 | 2018 |
| Correlating self-report and trace data measures of incivility: A proof of concept T Hopp, CJ Vargo, L Dixon, N Thain Social Science Computer Review 38 (5), 584-599, 2020 | 25 | 2020 |
| Pick's theorem via Minkowski's theorem MR Murty, N Thain The American Mathematical Monthly 114 (8), 732-736, 2007 | 25 | 2007 |
| Building healthy recommendation sequences for everyone: A safe reinforcement learning approach A Singh, Y Halpern, N Thain, K Christakopoulou, E Chi, J Chen, A Beutel FAccTRec Workshop, 2020 | 24 | 2020 |
| A theoretical examination of practical game playing: Lookahead search V Mirrokni, N Thain, A Vetta International Symposium on Algorithmic Game Theory, 251-262, 2012 | 23 | 2012 |
| Classifying constructive comments V Kolhatkar, N Thain, J Sorensen, L Dixon, M Taboada arXiv preprint arXiv:2004.05476, 2020 | 21 | 2020 |
Lucas DixonPAIR, Google ResearchVerified email at google.com
