# A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs

arXiv: https://arxiv.org/abs/2503.05050 · HTML: https://mlsanity.com/paper/2503.05050/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI](https://mlsanity.com/paper/2003.07258/) (2020)
- [What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research](https://mlsanity.com/paper/2102.07817/) (2021)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction](https://mlsanity.com/paper/2409.00265/) (2024)
- [ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspective](https://mlsanity.com/paper/2204.01888/) (2022)
- [Abstractive Text Summarization: State of the Art, Challenges, and Improvements](https://mlsanity.com/paper/2409.02413/) (2024)
- [Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms](https://mlsanity.com/paper/2410.00134/) (2024)
- [Ethio-Fake: Cutting-Edge Approaches to Combat Fake News in Under-Resourced Languages Using Explainable AI](https://mlsanity.com/paper/2410.02609/) (2024)
- [First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages](https://mlsanity.com/paper/2312.04764/) (2023)
- [Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models](https://mlsanity.com/paper/2501.15374/) (2025)
- [Explainability in Neural Networks for Natural Language Processing Tasks](https://mlsanity.com/paper/2412.18036/) (2024)
- [Evaluating Text Summaries Generated by Large Language Models Using OpenAI's GPT](https://mlsanity.com/paper/2405.04053/) (2024)
- [Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations](https://mlsanity.com/paper/2405.04039/) (2024)

## Built on by (most cited first, 7 of 7)

- [Explainable AI: XAI-Guided Context-Aware Data Augmentation](https://mlsanity.com/paper/2506.03484/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming](https://mlsanity.com/paper/2509.16835/) (2025)
- [Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework](https://mlsanity.com/paper/2509.05199/) (2025)
- [Bilingual Word Level Language Identification for Omotic Languages](https://mlsanity.com/paper/2509.07998/) (2025)
- [Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models](https://mlsanity.com/paper/2602.16608/) (2026)
- [Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models](https://mlsanity.com/paper/2602.02304/) (2026)

## Abstract (arXiv)

The increasing complexity of LLMs presents significant challenges to their transparency and interpretability, necessitating the use of eXplainable AI (XAI) techniques to enhance trustworthiness and usability. This study introduces a comprehensive evaluation framework with four novel metrics for assessing the effectiveness of five XAI techniques across five LLMs and two downstream tasks. We apply this framework to evaluate several XAI techniques LIME, SHAP, Integrated Gradients, Layer-wise Relevance Propagation (LRP), and Attention Mechanism Visualization (AMV) using the IMDB Movie Reviews and Tweet Sentiment Extraction datasets. The evaluation focuses on four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity. Our results show that LIME consistently achieves high scores across multiple LLMs and evaluation metrics, while AMV demonstrates superior Robustness and near-perfect Consistency. LRP excels in Contrastivity, particularly with more complex models. Our findings provide valuable insights into the strengths and limitations of different XAI methods, offering guidance for developing and selecting appropriate XAI techniques for LLMs.