5 papers
The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search
David Farr, Iain Cruickshank, Kate Starbird +1
Distributed agents in real-world settings frequently must coordinate under uncertainty with only partial observations. Coordination is necessary to share beliefs to aid in task com…
Expert-in-the-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection
David Farr, Kevin Talty, Alexandra Farr +3
As cyber threats become more sophisticated, rapid and accurate vulnerability detection is essential for maintaining secure systems. This study explores the use of Large Language Mo…
LLM Confidence Evaluation Measures in Zero-Shot CSS Classification
David Farr, Iain Cruickshank, Nico Manzonelli +3
Assessing classification confidence is critical for leveraging large language models (LLMs) in automated labeling tasks, especially in the sensitive domains presented by Computatio…
LLM Chain Ensembles for Scalable and Accurate Data Annotation
David Farr, Nico Manzonelli, Iain Cruickshank +2
The ability of large language models (LLMs) to perform zero-shot classification makes them viable solutions for data annotation in rapidly evolving domains where quality labeled da…
RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science
David Farr, Nico Manzonelli, Iain Cruickshank +1
Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, an…