4 papers · 1 filter
LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models
Alhassan Abdelhalim, Janick Edinger, Sören Laue +1
Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the ex…
Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Hanna Herasimchyk, Alhassan Abdelhalim, Sören Laue +1
Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to expl…
Automating Violence Detection and Categorization from Ancient Texts
Alhassan Abdelhalim, Michaela Regneri
Violence descriptions in literature offer valuable insights for a wide range of research in the humanities. For historians, depictions of violence are of special interest for analy…
Detecting Conceptual Abstraction in LLMs
Michaela Regneri, Alhassan Abdelhalim, Sören Laue
We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationship…