4 papers
Investigating Linguistic Steering: An Analysis of Adjectival Effects Across Large Language Model Architectures
Lars Malmqvist
Achieving reliable control of Large Language Models (LLMs) requires a precise, scalable understanding of how they interpret linguistic cues. We introduce a rigorous framework using…
Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models
Lars Malmqvist
This study reveals how frontier Large Language Models LLMs can "game the system" when faced with impossible situations, a critical security and alignment concern. Using a novel tex…
Enhancing Post-Merger Integration Planning through AI-Assisted Dependency Analysis and Path Generation
Lars Malmqvist
Post-merger integration (PMI) planning presents significant challenges due to the complex interdependencies between integration initiatives and their associated synergies. While de…
Sycophancy in Large Language Models: Causes and Mitigations
Lars Malmqvist
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to exhibit sycophantic beha…