3 papers
cs.LG2025
Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
Saeed AlMarri, Mathieu Ravaut, Kristof Juhasz +3
Large Language Models (LLMs) have attracted significant attention for classification tasks, offering a flexible alternative to trusted classical machine learning models like LightG…
cs.CL2025
Interpreting LLMs as Credit Risk Classifiers: Do Their Feature Explanations Align with Classical ML?
Saeed AlMarri, Kristof Juhasz, Mathieu Ravaut +3
Large Language Models (LLMs) are increasingly explored as flexible alternatives to classical machine learning models for classification tasks through zero-shot prompting. However,…
cs.LG2025
Residual Speech Embeddings for Tone Classification: Removing Linguistic Content to Enhance Paralinguistic Analysis
Hamdan Al Ahbabi, Gautier Marti, Saeed AlMarri +1
Self-supervised learning models for speech processing, such as wav2vec2, HuBERT, WavLM, and Whisper, generate embeddings that capture both linguistic and paralinguistic information…