no code implementations • 29 Feb 2024 • Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies.
no code implementations • 24 Aug 2023 • Maximilian Mozes, Xuanli He, Bennett Kleinberg, Lewis D. Griffin
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 safety- and security-related threats and vulnerabilities of LLMs, including in the context of potentially criminal activities.
no code implementations • 19 Jul 2023 • Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, Robert McHardy
Due to the fast pace of the field, it is difficult to identify the remaining challenges and already fruitful application areas.
no code implementations • 10 Mar 2023 • Lewis D Griffin, Bennett Kleinberg, Maximilian Mozes, Kimberly T Mai, Maria Vau, Matthew Caldwell, Augustine Marvor-Parker
Data was collected from 1000 human participants using an online experiment, and 1000 simulated participants using engineered prompts and LLM completion.
no code implementations • 13 Feb 2023 • Maximilian Mozes, Tolga Bolukbasi, Ann Yuan, Frederick Liu, Nithum Thain, Lucas Dixon
In this paper, we explore the use of TracIn to improve model performance in the parameter-efficient tuning (PET) setting.
no code implementations • 13 Feb 2023 • Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon
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 digital assistants and chatbots.
no code implementations • 20 Oct 2022 • Maximilian Mozes, Bennett Kleinberg, Lewis D. Griffin
Adversarial examples in NLP are receiving increasing research attention.
no code implementations • 27 Aug 2022 • 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).
no code implementations • 23 Sep 2021 • Maximilian Mozes, Martin Schmitt, Vladimir Golkov, Hinrich Schütze, Daniel Cremers
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-generated visual relationships to describe images in natural language.
1 code implementation • EMNLP 2021 • Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
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 validating these adversarial inputs against certain criteria (e. g., the preservation of semantics and grammaticality).
no code implementations • 7 Jul 2021 • 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.
no code implementations • 16 Mar 2021 • 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.
1 code implementation • 10 Sep 2020 • Isabelle van der Vegt, Maximilian Mozes, Bennett Kleinberg, Paul Gill
This paper introduces the Grievance Dictionary, a psycholinguistic dictionary which can be used to automatically understand language use in the context of grievance-fuelled violence threat assessment.
no code implementations • EACL 2021 • Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood.
5 code implementations • ACL 2020 • Bennett Kleinberg, Isabelle van der Vegt, Maximilian Mozes
This resulted in the Real World Worry Dataset of 5, 000 texts (2, 500 short + 2, 500 long texts).
no code implementations • 30 Aug 2019 • Isabelle van der Vegt, Maximilian Mozes, Paul Gill, Bennett Kleinberg
We also observe structural breakpoints in the use of bigrams at the time of the rally, suggesting there are changes in language use within the two groups as a result of the rally.
no code implementations • WS 2019 • Felix Soldner, Justin Chun-ting Ho, Mykola Makhortykh, Isabelle W.J. van der Vegt, Maximilian Mozes, Bennett Kleinberg
We found that the use of two sentiment patterns differed significantly depending on political leaning.
no code implementations • EMNLP 2018 • Bennett Kleinberg, Maximilian Mozes, Isabelle van der Vegt
Vlogs provide a rich public source of data in a novel setting.