Logo image
An Empirical Study of LLM-Generated Local Explanations for Linear Additive Models
Conference paper

An Empirical Study of LLM-Generated Local Explanations for Linear Additive Models

Ahmet Menevse, Rehan Raza, Marco Fisichella and Guanjin Wang
Machine Learning and Knowledge Engineering for Decision Making, pp.109-125
Lecture Notes in Computer Science, Springer Nature Singapore
The 17th International FLINS Conference on Fuzzy Logic for Intelligent Systems and The 21st International Conference on Intelligent Systems and Knowledge Engineering (Sydney, NSW, Australia, 15/07/2026–19/07/2026)
2027

Abstract

Explainable AI Large Language Model Local Explainer
Post-hoc local explanations are widely used to improve the transparency of AI predictions. However, their reliability varies across methods and data settings. This study investigates whether Large Language Models (LLMs), using structured prompting and in-context learning (ICL), can function as local explainers for tabular models and compares their performance with Local Interpretable Model-agnostic Explanations (LIME). We introduce a reproducible benchmarking framework to evaluate explanation quality by assessing each method’s ability to recover instance-level ground-truth feature contributions from linear additive models. This serves as a sanity check of local explanation validity. We further examine the influence of key factors, including the number of numerical and categorical features and the number of in-context examples (shots). Faithfulness is evaluated using the Model-Intrinsic Additive Scores (MIAS) metric, while robustness is assessed through standard insertion–deletion metrics across multiple public tabular datasets. Empirical results indicate that LLM-based local explanations do not consistently recover instance-level ground-truth contributions. While they perform comparably in low-shot settings, their performance plateaus or declines as additional contextual information is introduced.

Details

Metrics

1 Record Views
Logo image