Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Komeili, Mojtaba"'
Autor:
Dhuliawala, Shehzaad, Komeili, Mojtaba, Xu, Jing, Raileanu, Roberta, Li, Xian, Celikyilmaz, Asli, Weston, Jason
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their mistakes. We de
Externí odkaz:
http://arxiv.org/abs/2309.11495
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
Current dialogue research primarily studies pairwise (two-party) conversations, and does not address the everyday setting where more than two speakers converse together. In this work, we both collect and evaluate multi-party conversations to study th
Externí odkaz:
http://arxiv.org/abs/2304.13835
While language models have become more capable of producing compelling language, we find there are still gaps in maintaining consistency, especially when describing events in a dynamically changing world. We study the setting of generating narratives
Externí odkaz:
http://arxiv.org/abs/2301.05746
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
Autor:
Shuster, Kurt, Komeili, Mojtaba, Adolphs, Leonard, Roller, Stephen, Szlam, Arthur, Weston, Jason
Language models (LMs) have recently been shown to generate more factual responses by employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021). We extend the recent approach of Adolphs et al. (2021) to include inte
Externí odkaz:
http://arxiv.org/abs/2203.13224
The largest store of continually updating knowledge on our planet can be accessed via internet search. In this work we study giving access to this information to conversational agents. Large language models, even though they store an impressive amoun
Externí odkaz:
http://arxiv.org/abs/2107.07566
Publikováno v:
In Journal of Alloys and Compounds 10 December 2023 967