Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability with Local Explanations

2025-05-27 · Zeinab Dehghani, Mohammed Naveed Akram, Koorosh Aslansefat, Adil Khan

Large language models like GPT, LLAMA, and Claude have become incredibly powerful at generating text, but they are still black boxes, so it is hard to understand how they decide what to say. That lack of transparency can be problematic, especially in fields where trust and accountability matter. To help with this, we introduce SMILE, a new method that explains how these models respond to different parts of a prompt. SMILE is model-agnostic and works by slightly changing the input, measuring how the output changes, and then highlighting which words had the most impact. Create simple visual heat maps showing which parts of a prompt matter the most. We tested SMILE on several leading LLMs and used metrics such as accuracy, consistency, stability, and fidelity to show that it gives clear and reliable explanations. By making these models easier to understand, SMILE brings us one step closer to making AI more transparent and trustworthy.

📄 PDF Abstract BibTeX arXiv:2505.21657

Code (1)

dependable-intelligent-systems-lab/xwhy

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Addressing Explainability of Generative AI using SMILE (Statistical Model-agnostic Interpretability with Local Explanations)

2026-02-01 · Zeinab Dehghani arxiv

The rapid advancement of generative artificial intelligence has enabled models capable of producing complex textual and visual outputs; however, their decision-making processes remain largely opaque, limiting trust and a…

Image Editing

Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations

2023-11-13 · Koorosh Aslansefat, Mojgan Hashemian, Martin Walker, Mohammed Naveed Akram 외

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models…

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)Explainable Models Interpretable Machine Learning

Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations

2024-10-20 · Seyed Mohammad Ahmadi, Koorosh Aslansefat, Ruben Valcarce-Dineiro, Joshua Barnfather

In today's world, the significance of explainable AI (XAI) is growing in robotics and point cloud applications, as the lack of transparency in decision-making can pose considerable safety risks, particularly in autonomou…

Autonomous Driving

SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis

2026-09-04 · Yuqing Yang, Alexander Schmatz, Zhaozhao Ma, Changkyu Choi 외 arxiv

Explainability is increasingly seen as a crucial requirement in AI-based medical diagnosis, particularly in safety-critical clinical decision-making. Most existing explainability methods in healthcare operate in a post-h…

Medical Diagnosis

Mapping the Mind of an Instruction-based Image Editing using SMILE

2024-12-20 · Zeinab Dehghani, Koorosh Aslansefat, Adil Khan, Adín Ramírez Rivera 외

Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we intro…