Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis
This addresses the need for reliability and transparency in high-stakes sentiment analysis applications, though it is incremental as it adapts an existing method to LLMs.
The research tackled the interpretability problem in sentiment analysis with Large Language Models (LLMs) by applying SHAP to break down LLMs into components like embedding and attention layers, demonstrating a notable enhancement over existing explainability techniques on the SST-2 dataset.
Interpretability remains a key difficulty in sentiment analysis with Large Language Models (LLMs), particularly in high-stakes applications where it is crucial to comprehend the rationale behind forecasts. This research addressed this by introducing a technique that applies SHAP (Shapley Additive Explanations) by breaking down LLMs into components such as embedding layer,encoder,decoder and attention layer to provide a layer-by-layer knowledge of sentiment prediction. The approach offers a clearer overview of how model interpret and categorise sentiment by breaking down LLMs into these parts. The method is evaluated using the Stanford Sentiment Treebank (SST-2) dataset, which shows how different sentences affect different layers. The effectiveness of layer-wise SHAP analysis in clarifying sentiment-specific token attributions is demonstrated by experimental evaluations, which provide a notable enhancement over current whole-model explainability techniques. These results highlight how the suggested approach could improve the reliability and transparency of LLM-based sentiment analysis in crucial applications.