Eric Michael Smith
Eric Michael Smith
Meta AI
Verified email at - Homepage
Cited by
Cited by
Llama 2: Open foundation and fine-tuned chat models
H Touvron, L Martin, K Stone, P Albert, A Almahairi, Y Babaei, ...
arXiv preprint arXiv:2307.09288, 2023
Recipes for building an open-domain chatbot
S Roller, E Dinan, N Goyal, D Ju, M Williamson, Y Liu, J Xu, M Ott, ...
arXiv preprint arXiv:2004.13637, 2020
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
H Rashkin, EM Smith, M Li, YL Boureau
Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019
Multiple-attribute text rewriting
G Lample, S Subramanian, E Smith, L Denoyer, MA Ranzato, YL Boureau
Age 18 (24), 65, 2018
Can you put it all together: Evaluating conversational agents' ability to blend skills
EM Smith, M Williamson, K Shuster, J Weston, YL Boureau
arXiv preprint arXiv:2004.08449, 2020
Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage
K Shuster, J Xu, M Komeili, D Ju, EM Smith, S Roller, M Ung, M Chen, ...
arXiv preprint arXiv:2208.03188, 2022
Multiple-attribute text style transfer
S Subramanian, G Lample, EM Smith, L Denoyer, MA Ranzato, ...
arXiv preprint arXiv:1811.00552, 2018
Open-domain conversational agents: Current progress, open problems, and future directions
S Roller, YL Boureau, J Weston, A Bordes, E Dinan, A Fan, D Gunning, ...
arXiv preprint arXiv:2006.12442, 2020
I Know the Feeling: Learning to Converse with Empathy
H Rashkin, EM Smith, M Li, YL Boureau
arXiv preprint arXiv:1811.00207, 2018
“I’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset
EM Smith, M Hall, M Kambadur, E Presani, A Williams
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
Human evaluation of conversations is an open problem: comparing the sensitivity of various methods for evaluating dialogue agents
EM Smith, O Hsu, R Qian, S Roller, YL Boureau, J Weston
arXiv preprint arXiv:2201.04723, 2022
Controlling style in generated dialogue
EM Smith, D Gonzalez-Rico, E Dinan, YL Boureau
arXiv preprint arXiv:2009.10855, 2020
Perturbation augmentation for fairer nlp
R Qian, C Ross, J Fernandes, E Smith, D Kiela, A Williams
arXiv preprint arXiv:2205.12586, 2022
Multi-modal open-domain dialogue
K Shuster, EM Smith, D Ju, J Weston
arXiv preprint arXiv:2010.01082, 2020
Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models
EM Smith, A Williams
arXiv preprint arXiv:2109.03300, 2021
Mapping local optical densities of states in silicon photonic structures with nanoscale electron spectroscopy
JJ Cha, Z Yu, E Smith, M Couillard, S Fan, DA Muller
Physical Review B 81 (11), 113102, 2010
" I'm sorry to hear that": finding bias in language models with a holistic descriptor dataset
EM Smith, MHM Kambadur, E Presani, A Williams
arXiv preprint arXiv:2205.09209, 2022
Zero-shot fine-grained style transfer: Leveraging distributed continuous style representations to transfer to unseen styles
EM Smith, D Gonzalez-Rico, E Dinan, YL Boureau
arXiv preprint arXiv:1911.03914, 2019
Toxicity in multilingual machine translation at scale
MR Costa-jussą, E Smith, C Ropers, D Licht, J Maillard, J Ferrando, ...
arXiv preprint arXiv:2210.03070, 2022
Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale
MR Costa-jussą, P Andrews, E Smith, P Hansanti, C Ropers, E Kalbassi, ...
arXiv preprint arXiv:2305.13198, 2023
The system can't perform the operation now. Try again later.
Articles 1–20