Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917958288146432 |
|---|---|
| author | Thogesan, Thivya Nugaliyadde, Anupiya Wong, Kok Wai |
| author_facet | Thogesan, Thivya Nugaliyadde, Anupiya Wong, Kok Wai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11948 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis Thogesan, Thivya Nugaliyadde, Anupiya Wong, Kok Wai Computation and Language Artificial Intelligence 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. |
| title | Integration of Explainable AI Techniques with Large Language Models for Enhanced Interpretability for Sentiment Analysis |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.11948 |