Maximilian Mozes

33 papers A* 3A 1Journal 23Unranked 4
YearRankTypeTitle / Venue / Authors
2025 J jnl
LLMs can implicitly learn from mistakes in-context.
CoRR
Lisa Alazraki, Maximilian Mozes, Jon Ander Campos, Yi Chern Tan, Marek Rei, Max Bartolo
2025 A* conf
No Need for Explanations: LLMs can implicitly learn from mistakes in-context.
EMNLP
Lisa Alazraki, Maximilian Mozes, Jon Ander Campos, Yi Chern Tan, Marek Rei, Max Bartolo
2025 A* conf
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models.
ICLR
Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwaraknath Gnaneshwar, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, Max Bartolo
2025 J jnl
Reverse Engineering Human Preferences with Reinforcement Learning.
CoRR
Lisa Alazraki, Yi Chern Tan, Jon Ander Campos, Maximilian Mozes, Marek Rei, Max Bartolo
2024 — conf
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge.
ACL (Findings)
Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu
2024 J jnl
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge.
CoRR
Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu
2024 J jnl
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models.
CoRR
Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwarak Talupuru, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, Max Bartolo
2023 J jnl
Challenges and Applications of Large Language Models.
CoRR
Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, Robert McHardy
2023 J jnl
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning.
CoRR
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan, Frederick Liu, Nithum Thain, Lucas Dixon
2023 — ed.
Proceedings of the 8th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2023, Toronto, Canada, July 13, 2023.
RepL4NLP@ACL
Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
2023 J jnl
Susceptibility to Influence of Large Language Models.
CoRR
Lewis D. Griffin, Bennett Kleinberg, Maximilian Mozes, Kimberly T. Mai, Maria Vau, Matthew Caldwell, Augustine Marvor-Parker
2023 — conf
Towards Agile Text Classifiers for Everyone.
EMNLP (Findings)
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon
2023 J jnl
Towards Agile Text Classifiers for Everyone.
CoRR
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon
2023 J jnl
Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities.
CoRR
Maximilian Mozes, Xuanli He, Bennett Kleinberg, Lewis D. Griffin
2022 — conf
Identifying Human Strategies for Generating Word-Level Adversarial Examples.
EMNLP (Findings)
Maximilian Mozes, Bennett Kleinberg, Lewis D. Griffin
2022 J jnl
Identifying Human Strategies for Generating Word-Level Adversarial Examples.
CoRR
Maximilian Mozes, Bennett Kleinberg, Lewis D. Griffin
2022 — ed.
Proceedings of the 7th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2022, Dublin, Ireland, May 26, 2022
RepL4NLP@ACL
Spandana Gella, He He, Bodhisattwa Prasad Majumder, Burcu Can, Eleonora Giunchiglia, Samuel Cahyawijaya, Sewon Min, Maximilian Mozes, Xiang Lorraine Li, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Laura Rimell, Chris Dyer
2022 J jnl
Textwash - automated open-source text anonymisation.
CoRR
Bennett Kleinberg, Toby Davies, Maximilian Mozes
2021 — conf
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification.
EMNLP (1)
Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
2021 J jnl
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification.
CoRR
Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
2021 J jnl
Correction to: Online influence, offline violence: language use on YouTube surrounding the 'Unite the Right' rally.
J. Comput. Soc. Sci.
Isabelle van der Vegt, Maximilian Mozes, Paul Gill, Bennett Kleinberg
2021 A conf
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples.
EACL
Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
2021 J jnl
No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization.
CoRR
Maximilian Mozes, Bennett Kleinberg
2021 J jnl
Online influence, offline violence: language use on YouTube surrounding the 'Unite the Right' rally.
J. Comput. Soc. Sci.
Isabelle van der Vegt, Maximilian Mozes, Paul Gill, Bennett Kleinberg
2021 J jnl
Scene Graph Generation for Better Image Captioning?
CoRR
Maximilian Mozes, Martin Schmitt, Vladimir Golkov, Hinrich Schütze, Daniel Cremers
2021 J jnl
Worry, coping and resignation - A repeated-measures study on emotional responses after a year in the pandemic.
CoRR
Maximilian Mozes, Isabelle van der Vegt, Bennett Kleinberg
2020 J jnl
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples.
CoRR
Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin
2020 J jnl
Measuring Emotions in the COVID-19 Real World Worry Dataset.
CoRR
Bennett Kleinberg, Isabelle van der Vegt, Maximilian Mozes
2020 J jnl
The Grievance Dictionary: Understanding Threatening Language Use.
CoRR
Isabelle van der Vegt, Maximilian Mozes, Bennett Kleinberg, Paul Gill
2019 J jnl
Online influence, offline violence: Linguistic responses to the 'Unite the Right' rally.
CoRR
Isabelle van der Vegt, Maximilian Mozes, Paul Gill, Bennett Kleinberg
2018 A* conf
Identifying the narrative styles of YouTube's vloggers.
EMNLP
Bennett Kleinberg, Maximilian Mozes, Isabelle van der Vegt
2018 J jnl
Identifying the sentiment styles of YouTube's vloggers.
CoRR
Bennett Kleinberg, Maximilian Mozes, Isabelle van der Vegt
2017 J jnl
Web-based text anonymization with Node.js: Introducing NETANOS (Named entity-based Text Anonymization for Open Science).
J. Open Source Softw.
Bennett Kleinberg, Maximilian Mozes