12 citations · 14 across the 5 of their papers we have counts for
5 papers
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
Paul Darm, Cem Alpturk, Kenneth Ulrich +3
Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their r…
Inference-Time Intervention in Large Language Models for Reliable Requirement Verification
Paul Darm, James Xie, Annalisa Riccardi
Steering the behavior of Large Language Models (LLMs) remains a challenge, particularly in engineering applications where precision and reliability are critical. While fine-tuning…
Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models
Paul Darm, Annalisa Riccardi
Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate…
FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM
Grace Colverd, Paul Darm, Leonard Silverberg +1
Fast disaster impact reporting is crucial in planning humanitarian assistance. Large Language Models (LLMs) are well known for their ability to write coherent text and fulfill a va…
Knowledge Base Question Answering for Space Debris Queries
Paul Darm, Antonio Valerio Miceli-Barone, Shay B. Cohen +1
Space agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge bases (KB) are…