activity
20212026
most citedWarning: Humans Cannot Reliably Detect Speech Deepfakes

90 citations · 137 across the 12 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2024★ 1 cited

Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas

Louis Kwok, Michal Bravansky, Lewis D. Griffin

The success of Large Language Models (LLMs) in multicultural environments hinges on their ability to understand users' diverse cultural backgrounds. We measure this capability by h…

cs.CL2023★ 29 cited

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…

cs.CL2023★ 8 cited

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…

cs.CL2022

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…

cs.CL2022★ 5 cited

Self-Supervised Losses for One-Class Textual Anomaly Detection

Kimberly T. Mai, Toby Davies, Lewis D. Griffin

Current deep learning methods for anomaly detection in text rely on supervisory signals in inliers that may be unobtainable or bespoke architectures that are difficult to tune. We…

cs.CL2021

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…