16 papers
Quantifying Retriever-Generator Alignment in RAG with Local Explanations
Korbinian Randl, Guido Rocchietti, Aron Henriksson +3
Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground their outputs in external documents. However, the interaction between these comp…
Aristotelian Virtue Profiling of LLMs through Ethical Dilemmas
Ioannis Tzachristas, John Pavlopoulos
Large Language Models (LLMs) often face ethical tradeoffs in which several responses may be defensible but express different priorities, such as fairness, honesty, courage, or rest…
Learning Diachronic Representations of Ancient Greek Letterforms
John Pavlopoulos, Spyros Barbakos, Lavinia Ferretti +7
Learning representations that remain robust across centuries of variation in handwriting is a key challenge in diachronic representation learning. Taking one of the longest continu…
CAKE: Confidence in Assignments via K-partition Ensembles
Aggelos Semoglou, John Pavlopoulos
Clustering is widely used for unsupervised structure discovery, yet it offers limited insight into how reliable each individual assignment is. Diagnostics, such as convergence beha…
Composite Silhouette: A Subsampling-based Aggregation Strategy
Aggelos Semoglou, Aristidis Likas, John Pavlopoulos
Determining the number of clusters is a central challenge in unsupervised learning, where ground-truth labels are unavailable. The Silhouette coefficient is a widely used internal…
Silhouette-Driven Instance-Weighted -means
Aggelos Semoglou, Aristidis Likas, John Pavlopoulos
Clustering is a fundamental unsupervised learning task with applications across a wide range of domains. Popular algorithms such as -means are efficient and widely used, but can…