90 citations · 140 across the 13 of their papers we have counts for
13 papers
Watson & Holmes: A Naturalistic Benchmark for Comparing Human and LLM Reasoning
Thatchawin Leelawat, Lewis D Griffin
Existing benchmarks for AI reasoning provide limited insight into how closely these capabilities resemble human reasoning in naturalistic contexts. We present an adaptation of the…
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…
Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning
Augustine N. Mavor-Parker, Matthew J. Sargent, Caswell Barry +2
Periodic activation functions, often referred to as learned Fourier features have been widely demonstrated to improve sample efficiency and stability in a variety of deep RL algori…
Transcript of GPT-4 playing a rogue AGI in a Matrix Game
Lewis D Griffin, Nicholas Riggs
Matrix Games are a type of unconstrained wargame used by planners to explore scenarios. Players propose actions, and give arguments and counterarguments for their success. An umpir…
Understanding the limitations of self-supervised learning for tabular anomaly detection
Kimberly T. Mai, Toby Davies, Lewis D. Griffin
While self-supervised learning has improved anomaly detection in computer vision and natural language processing, it is unclear whether tabular data can benefit from it. This paper…
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…
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…
Warning: Humans Cannot Reliably Detect Speech Deepfakes
Kimberly T. Mai, Sergi D. Bray, Toby Davies +1
Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progr…
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…
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Augustine N. Mavor-Parker, Matthew J. Sargent, Christian Pehle +3
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount…
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…
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…
Brittle Features May Help Anomaly Detection
Kimberly T. Mai, Toby Davies, Lewis D. Griffin
One-class anomaly detection is challenging. A representation that clearly distinguishes anomalies from normal data is ideal, but arriving at this representation is difficult since…