Följ
Maximilian Mozes
Maximilian Mozes
Cohere
Verifierad e-postadress på cohere.com - Startsida
Titel
Citeras av
Citeras av
År
Challenges and applications of large language models
J Kaddour, J Harris, M Mozes, H Bradley, R Raileanu, R McHardy
arXiv preprint arXiv:2307.10169, 2023
5152023
Measuring emotions in the covid-19 real world worry dataset
B Kleinberg, I van der Vegt, M Mozes
NLP COVID-19 Workshop, ACL 2020, 2020
226*2020
Frequency-guided word substitutions for detecting textual adversarial examples
M Mozes, P Stenetorp, B Kleinberg, LD Griffin
EACL 2021, 2020
1042020
Use of llms for illicit purposes: Threats, prevention measures, and vulnerabilities
M Mozes, X He, B Kleinberg, LD Griffin
arXiv preprint arXiv:2308.12833, 2023
902023
Using named entities for computer‐automated verbal deception detection
B Kleinberg, M Mozes, A Arntz, B Verschuere
Journal of forensic sciences 63 (3), 714-723, 2018
642018
The grievance dictionary: Understanding threatening language use
I van der Vegt, M Mozes, B Kleinberg, P Gill
Behavior research methods, 1-15, 2021
502021
Online influence, offline violence: language use on YouTube surrounding the ‘Unite the Right’rally
I Van der Vegt, M Mozes, P Gill, B Kleinberg
Journal of Computational Social Science 4, 333-354, 2021
382021
Challenges and applications of large language models. arXiv 2023
J Kaddour, J Harris, M Mozes, H Bradley, R Raileanu, R McHardy
arXiv preprint arXiv:2307.10169 10, 2024
362024
Identifying the sentiment styles of YouTube's vloggers
B Kleinberg, M Mozes, I van der Vegt
EMNLP 2018, 2018
282018
No intruder, no validity: evaluation criteria for privacy-preserving text anonymization
M Mozes, B Kleinberg
arXiv preprint arXiv:2103.09263, 2021
232021
Susceptibility to influence of large language models
LD Griffin, B Kleinberg, M Mozes, KT Mai, M Vau, M Caldwell, ...
arXiv preprint arXiv:2303.06074, 2023
212023
Netanos-named entity-based text anonymization for open science
B Kleinberg, M Mozes, Y van der Toolen
OSF, 2017
202017
Large language models respond to influence like humans
L Griffin, B Kleinberg, M Mozes, K Mai, MDM Vau, M Caldwell, ...
Proceedings of the First Workshop on Social Influence in Conversations …, 2023
192023
Challenges and applications of large language models (2023)
J Kaddour, J Harris, M Mozes, H Bradley, R Raileanu, R McHardy
arXiv preprint arXiv:2307.10169 4, 2024
162024
Web-based text anonymization with Node.js: Introducing NETANOS (Named entity-based Text Anonymization for Open Science)
MM Bennett Kleinberg
The Journal of Open Source Software 2 (14), 2017
142017
A repeated-measures study on emotional responses after a year in the pandemic
M Mozes, I van der Vegt, B Kleinberg
Scientific reports 11 (1), 23114, 2021
132021
Here's a free lunch: Sanitizing backdoored models with model merge
A Arora, X He, M Mozes, S Swain, M Dras, Q Xu
arXiv preprint arXiv:2402.19334, 2024
112024
Textwash--automated open-source text anonymisation
B Kleinberg, T Davies, M Mozes
arXiv preprint arXiv:2208.13081, 2022
112022
Contrasting human-and machine-generated word-level adversarial examples for text classification
M Mozes, M Bartolo, P Stenetorp, B Kleinberg, LD Griffin
EMNLP 2021, 2021
112021
Uphill from here: Sentiment patterns in videos from left-and right-wingYouTube news channels
F Soldner, JCT Ho, M Makhortykh, I Van der Vegt, M Mozes, B Kleinberg
Workshop on Natural Language Processing and Computational Social Science 3 …, 2019
112019
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20