2 papers
cs.CL2025
NormXLogit: The Head-on-Top Never Lies
Sina Abbasi, Mohammad Reza Modarres, Mohammad Taher Pilehvar
With new large language models (LLMs) emerging frequently, it is important to consider the potential value of model-agnostic approaches that can provide interpretability across a v…
cs.CL2024
RepMatch: Quantifying Cross-Instance Similarities in Representation Space
Mohammad Reza Modarres, Sina Abbasi, Mohammad Taher Pilehvar
Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attribu…