19 citations · 43 across the 14 of their papers we have counts for
15 papers
War Elephants: Rethinking Combat AI and Human Oversight
Philip Feldman, Aaron Dant, Harry Dreany
This paper explores the changes that pervasive AI is having on the nature of combat. We look beyond the substitution of AI for experts to an approach where complementary human and…
Killer Apps: Low-Speed, Large-Scale AI Weapons
Philip Feldman, Aaron Dant, James R. Foulds
The accelerating advancements in Artificial Intelligence (AI) and Machine Learning (ML), highlighted by the development of cutting-edge Generative Pre-trained Transformer (GPT) mod…
Trapping LLM Hallucinations Using Tagged Context Prompts
Philip Feldman, James R. Foulds, Shimei Pan
Recent advances in large language models (LLMs), such as ChatGPT, have led to highly sophisticated conversation agents. However, these models suffer from "hallucinations," where th…
Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech
Jarod Govers, Philip Feldman, Aaron Dant +1
Social media is a modern person's digital voice to project and engage with new ideas and mobilise communities $\unicode{x2013}$ a power shared with extremists. Given the societal r…
The Keyword Explorer Suite: A Toolkit for Understanding Online Populations
Philip Feldman, Shimei Pan, James R. Foulds
We have developed a set of Python applications that use large language models to identify and analyze data from social media platforms relevant to a population of interest. Our pip…
Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models
Philip Feldman, Aaron Dant, James R. Foulds +1
Text analysis of social media for sentiment, topic analysis, and other analysis depends initially on the selection of keywords and phrases that will be used to create the research…
Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models
Philip Feldman, Aaron Dant, David Rosenbluth
The problem of determining if a military unit has correctly understood an order and is properly executing on it is one that has bedeviled military planners throughout history. The…
Analyzing COVID-19 Tweets with Transformer-based Language Models
Philip Feldman, Sim Tiwari, Charissa S. L. Cheah +2
This paper describes a method for using Transformer-based Language Models (TLMs) to understand public opinion from social media posts. In this approach, we train a set of GPT model…
Navigating Human Language Models with Synthetic Agents
Philip Feldman, Antonio Bucchiarone
Modern natural language models such as the GPT-2/GPT-3 contain tremendous amounts of information about human belief in a consistently testable form. If these models could be shown…
Training robust anomaly detection using ML-Enhanced simulations
Philip Feldman
This paper describes the use of neural networks to enhance simulations for subsequent training of anomaly-detection systems. Simulations can provide edge conditions for anomaly det…
Belief places and spaces: Mapping cognitive environments
Philip Feldman, Aaron Dant, Wayne Lutters
Beliefs are not facts, but they are factive - they feel like facts. This property is what can make misinformation dangerous. Being able to deliberately navigate through a landscape…
Dungeons for Science: Mapping Belief Places and Spaces
Aaron Dant, Philip Feldman, Wayne Lutters
Tabletop fantasy role-playing games (TFRPGs) have existed in offline and online contexts for many decades, yet are rarely featured in scientific literature. This paper presents a c…
Disrupting the Coming Robot Stampedes: Designing Resilient Information Ecologies
Philip Feldman, Aaron Dant, Wayne Lutters
Machines are designed to communicate widely and efficiently. Humans, less so. We evolved social structures that function best as small subgroups interacting within larger populatio…
Simon's Anthill: Mapping and Navigating Belief Spaces
Philip Feldman, Aaron Dant, Wayne Lutters
In the parable of Simon's Ant, an ant follows a complex path along a beach on to reach its goal. The story shows how the interaction of simple rules and a complex environment resul…
This One Simple Trick Disrupts Digital Communities
Philip Feldman, Aaron Dant, Wayne Lutters
This paper describes an agent based simulation used to model human actions in belief space, a high-dimensional subset of information space associated with opinions. Using insights…