Maximilian Mozes
University College London
H-index: 11
Europe-United Kingdom
Top articles of Maximilian Mozes
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge
arXiv preprint arXiv:2402.19334
2024/2/29
Use of llms for illicit purposes: Threats, prevention measures, and vulnerabilities
arXiv preprint arXiv:2308.12833
2023/8/24
Challenges and applications of large language models
2023/7/19
Large language models respond to influence like humans
2023/7
Maximilian Mozes
H-Index: 5
Augustine Mavor-Parker
H-Index: 1
Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
2023/7
Susceptibility to influence of large language models
arXiv preprint arXiv:2303.06074
2023/3/10
Towards agile text classifiers for everyone
arXiv preprint arXiv:2302.06541
2023/2/13
Maximilian Mozes
H-Index: 5
Gradient-based automated iterative recovery for parameter-efficient tuning
arXiv preprint arXiv:2302.06598
2023/2/13
Maximilian Mozes
H-Index: 5
Textwash--automated open-source text anonymisation
arXiv preprint arXiv:2208.13081
2022/8/27
Toby Davies
H-Index: 11
Maximilian Mozes
H-Index: 5
Identifying Human Strategies for Generating Word-Level Adversarial Examples
arXiv preprint arXiv:2210.11598
2022/10/20
Maximilian Mozes
H-Index: 5
Lewis D Griffin
H-Index: 23
A repeated-measures study on emotional responses after a year in the pandemic
Scientific reports
2021/11/30
Maximilian Mozes
H-Index: 5
Isabelle Van Der Vegt
H-Index: 6
The grievance dictionary: Understanding threatening language use
Behavior Research Methods
2021/3/23
Scene graph generation for better image captioning?
arXiv preprint arXiv:2109.11398
2021/9/23
Maximilian Mozes
H-Index: 5
Martin Schmitt
H-Index: 3
Vladimir Golkov
H-Index: 10
Hinrich Schütze
H-Index: 48
Daniel Cremers
H-Index: 77
Contrasting human-and machine-generated word-level adversarial examples for text classification
EMNLP 2021
2021/9/9
Worry, coping and resignation--A repeated-measures study on emotional responses after a year in the pandemic
2021/7/7
Maximilian Mozes
H-Index: 5
Online influence, offline violence: language use on YouTube surrounding the ‘Unite the Right’rally
Journal of Computational Social Science
2021/5
No intruder, no validity: Evaluation criteria for privacy-preserving text anonymization
arXiv preprint arXiv:2103.09263
2021/3/16
Maximilian Mozes
H-Index: 5
Frequency-guided word substitutions for detecting textual adversarial examples
EACL 2021
2020/4/13
Maximilian Mozes
H-Index: 5
Lewis D Griffin
H-Index: 23
Measuring emotions in the covid-19 real world worry dataset
NLP COVID-19 Workshop, ACL 2020
2020/4/8
Isabelle Van Der Vegt
H-Index: 6
Maximilian Mozes
H-Index: 5
Co-Authors
