5 papers
Many Perturbations, Shared Failure Dynamics: Tracing Direction-Sensitive Perturbation Influence in Language Models
Zhibo Hu, Chen Wang, Yanfeng Shu +3
Why can a task-preserving rewrite turn a correct answer into a failure while a larger internal change leaves the answer intact? We develop a direction-sensitive, readout-relative a…
Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation
Zhibo Hu, Chen Wang, Yanfeng Shu +3
Large language models benefit from elements in natural language, such as metaphors and analogies in training data and inference input to achieve generalisability across different d…
Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models
Zhibo Hu, Chen Wang, Yanfeng Shu +2
Earlier research has shown that metaphors influence human decision-making, raising the question of whether metaphors also influence large language models (LLMs)' reasoning pathways…
Ambiguity in LLMs is a concept missing problem
Zhibo Hu, Chen Wang, Yanfeng Shu +2
Ambiguity in natural language is a significant obstacle for achieving accurate text to structured data mapping through large language models (LLMs), which affects the performance o…
Local Differential Privacy for Smart Meter Data Sharing
Yashothara Shanmugarasa, M. A. P. Chamikara, Hye-young Paik +2
Energy disaggregation techniques, which use smart meter data to infer appliance energy usage, can provide consumers and energy companies valuable insights into energy management. H…