Zobrazeno 1 - 10
of 76 189
pro vyhledávání: '"Y Lan"'
Many cognitive approaches to well-being, such as recognizing and reframing unhelpful thoughts, have received considerable empirical support over the past decades, yet still lack truly widespread adoption in self-help format. A barrier to that adoptio
Externí odkaz:
http://arxiv.org/abs/2307.02768
Autor:
Behrooz, Morteza, Ngan, William, Lane, Joshua, Morse, Giuliano, Babcock, Benjamin, Shuster, Kurt, Komeili, Mojtaba, Chen, Moya, Kambadur, Melanie, Boureau, Y-Lan, Weston, Jason
Publicly deploying research chatbots is a nuanced topic involving necessary risk-benefit analyses. While there have recently been frequent discussions on whether it is responsible to deploy such models, there has been far less focus on the interactio
Externí odkaz:
http://arxiv.org/abs/2306.04765
Autor:
Xu, Jing, Ju, Da, Lane, Joshua, Komeili, Mojtaba, Smith, Eric Michael, Ung, Megan, Behrooz, Morteza, Ngan, William, Moritz, Rashel, Sukhbaatar, Sainbayar, Boureau, Y-Lan, Weston, Jason, Shuster, Kurt
We present BlenderBot 3x, an update on the conversational model BlenderBot 3, which is now trained using organic conversation and feedback data from participating users of the system in order to improve both its skills and safety. We are publicly rel
Externí odkaz:
http://arxiv.org/abs/2306.04707
Publikováno v:
Geoscientific Model Development, Vol 17, Pp 3897-3918 (2024)
This study uses the Community Atmosphere Model 5.3 coupled to a 1-D ocean model to investigate the effects of intraseasonal sea surface temperature (SST) feedback frequency on Madden–Julian oscillation (MJO) simulations with intervals at 30 min and
Externí odkaz:
https://doaj.org/article/c7b8ab2d668a42378989d9880e4b9c6d
Autor:
Núñez, César Viloria1 cesar.viloria@ieee.org, Fruto, Jennifer Freja2 jenny-freja@ieee.org, Meisel, Yezid Donoso3 ydonoso@uniandes.edu.co
Publikováno v:
Ingeniería y Desarrollo. ene-jun2008, Issue 23, p84-103. 20p. 3 Diagrams, 6 Charts, 15 Graphs.
Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting to new inf
Externí odkaz:
http://arxiv.org/abs/2208.03270
Autor:
Shuster, Kurt, Xu, Jing, Komeili, Mojtaba, Ju, Da, Smith, Eric Michael, Roller, Stephen, Ung, Megan, Chen, Moya, Arora, Kushal, Lane, Joshua, Behrooz, Morteza, Ngan, William, Poff, Spencer, Goyal, Naman, Szlam, Arthur, Boureau, Y-Lan, Kambadur, Melanie, Weston, Jason
We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and co
Externí odkaz:
http://arxiv.org/abs/2208.03188
The promise of interaction between intelligent conversational agents and humans is that models can learn from such feedback in order to improve. Unfortunately, such exchanges in the wild will not always involve human utterances that are benign or of
Externí odkaz:
http://arxiv.org/abs/2208.03295
Autor:
Smith, Eric Michael, Hsu, Orion, Qian, Rebecca, Roller, Stephen, Boureau, Y-Lan, Weston, Jason
At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023), with human evaluations still considered the gold standard. Unfortunat
Externí odkaz:
http://arxiv.org/abs/2201.04723
Current open-domain conversational models can easily be made to talk in inadequate ways. Online learning from conversational feedback given by the conversation partner is a promising avenue for a model to improve and adapt, so as to generate fewer of
Externí odkaz:
http://arxiv.org/abs/2110.07518