no code implementations • 22 Sep 2024 • Yiming Zhang, Jianfeng Chi, Hailey Nguyen, Kartikeya Upasani, Daniel M. Bikel, Jason Weston, Eric Michael Smith
In the context of language model safety, when a partial unsafe generation is produced, language models by their nature tend to happily keep on generating similarly unsafe additional text.
no code implementations • 1 Apr 2024 • Yi-Lin Tuan, Xilun Chen, Eric Michael Smith, Louis Martin, Soumya Batra, Asli Celikyilmaz, William Yang Wang, Daniel M. Bikel
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience.
no code implementations • 11 Nov 2023 • Hsuan Su, Rebecca Qian, Chinnadhurai Sankar, Shahin Shayandeh, Shang-Tse Chen, Hung-Yi Lee, Daniel M. Bikel
In this paper, we propose a diagnosis method to attribute bias to each component of a TOD system.
1 code implementation • 14 Apr 2022 • Zhe Dong, Jianmo Ni, Daniel M. Bikel, Enrique Alfonseca, YuAn Wang, Chen Qu, Imed Zitouni
We further explore and explain why parameter sharing in projection layer significantly improves the efficacy of the dual encoders, by directly probing the embedding spaces of the two encoder towers with t-SNE algorithm.
no code implementations • ACL 2021 • Nicholas FitzGerald, Jan A. Botha, Daniel Gillick, Daniel M. Bikel, Tom Kwiatkowski, Andrew McCallum
We present an instance-based nearest neighbor approach to entity linking.
no code implementations • 7 Apr 2020 • Oshin Agarwal, Daniel M. Bikel
Recently, a solution has been proposed for the former as a dual-encoder entity retrieval system (Gillick et al., 2019) that learns mention and entity representations in the same space, and performs linking by selecting the nearest entity to the mention in this space.