180 citations · 321 across the 13 of their papers we have counts for
16 papers
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Maximilian Mozes, Xuanli He, Bennett Kleinberg +1
Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safet…
Challenges and Applications of Large Language Models
Jean Kaddour, Joshua Harris, Maximilian Mozes +3
Large Language Models (LLMs) went from non-existent to ubiquitous in the machine learning discourse within a few years. Due to the fast pace of the field, it is difficult to identi…
Susceptibility to Influence of Large Language Models
Lewis D Griffin, Bennett Kleinberg, Maximilian Mozes +4
Two studies tested the hypothesis that a Large Language Model (LLM) can be used to model psychological change following exposure to influential input. The first study tested a gene…
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan +3
Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their…
Towards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek +5
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digi…
Identifying Human Strategies for Generating Word-Level Adversarial Examples
Maximilian Mozes, Bennett Kleinberg, Lewis D. Griffin
Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transform…
Textwash -- automated open-source text anonymisation
Bennett Kleinberg, Toby Davies, Maximilian Mozes
The increased use of text data in social science research has benefited from easy-to-access data (e.g., Twitter). That trend comes at the cost of research requiring sensitive but h…
Scene Graph Generation for Better Image Captioning?
Maximilian Mozes, Martin Schmitt, Vladimir Golkov +2
We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generate…
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Maximilian Mozes, Max Bartolo, Pontus Stenetorp +2
Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validat…
A repeated-measures study on emotional responses after a year in the pandemic
Maximilian Mozes, Isabelle van der Vegt, Bennett Kleinberg
The introduction of COVID-19 lockdown measures and an outlook on return to normality are demanding societal changes. Among the most pressing questions is how individuals adjust to…
No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization
Maximilian Mozes, Bennett Kleinberg
For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws. There is hence a growing intere…
The Grievance Dictionary: Understanding Threatening Language Use
Isabelle van der Vegt, Maximilian Mozes, Bennett Kleinberg +1
This paper introduces the Grievance Dictionary, a psycholinguistic dictionary which can be used to automatically understand language use in the context of grievance-fuelled violenc…
Measuring Emotions in the COVID-19 Real World Worry Dataset
Bennett Kleinberg, Isabelle van der Vegt, Maximilian Mozes
The COVID-19 pandemic is having a dramatic impact on societies and economies around the world. With various measures of lockdowns and social distancing in place, it becomes importa…
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg +1
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show th…
Online influence, offline violence: Language Use on YouTube surrounding the 'Unite the Right' rally
Isabelle van der Vegt, Maximilian Mozes, Paul Gill +1
The media frequently describes the 2017 Charlottesville 'Unite the Right' rally as a turning point for the alt-right and white supremacist movements. Social movement theory suggest…
Identifying the sentiment styles of YouTube's vloggers
Bennett Kleinberg, Maximilian Mozes, Isabelle van der Vegt
Vlogs provide a rich public source of data in a novel setting. This paper examined the continuous sentiment styles employed in 27,333 vlogs using a dynamic intra-textual approach t…