Inherent Interpretability

Inherent interpretability in machine learning focuses on designing models and methods that are inherently transparent and understandable, aiming to reduce the "black box" nature of many AI systems. Current research emphasizes developing intrinsically interpretable model architectures, such as those based on decision trees, rule-based systems, and specific neural network designs (e.g., Kolmogorov-Arnold Networks), alongside techniques like feature attribution and visualization methods to enhance understanding of model behavior. This pursuit is crucial for building trust in AI, particularly in high-stakes applications like healthcare and finance, where understanding model decisions is paramount for responsible deployment and effective human-AI collaboration.

Papers

July 25, 2024

Network Inversion of Convolutional Neural Nets
Pirzada Suhail, Amit Sethi
Neural Network Inherent Interpretability Deep Convolutional Neural Network Adversarial Sample Network Inversion

July 22, 2024

A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting
Pierre-Daniel Arsenault, Shengrui Wang, Jean-Marc Patenande
Timely Survey Inherent Interpretability High Explainability Explainable Artificial Intelligence XAI Method xAI Community Financial Time Series

July 21, 2024

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
Erik Cambria, Lorenzo Malandri, Fabio Mercorio, Navid Nobani, Andrea Seveso
Medical LLM Inherent Interpretability Explainable AI xAI Community Model Interpretability eXplainable Artificial Intelligence Relational Information

July 19, 2024

Refining Tuberculosis Detection in CXR Imaging: Addressing Bias in Deep Neural Networks via Interpretability
Özgür Acar Güler, Manuel Günther, André Anjos
Deep Neural Network Deep Learning Model Inherent Interpretability Classification Performance Unseen Data Automatic Classification Tuberculosis Treatment Addressing Bias Tuberculosis Detection CXR Imaging

July 18, 2024

July 17, 2024

July 16, 2024

July 12, 2024

July 8, 2024

Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis
Nataliia Molchanova, Alessandro Cagol, Pedro M. Gordaliza, Mario Ocampo-Pineda, Po-Jui Lu, Matthias Weigel, Xinjie Chen, Adrien Depeursinge, Cristina Granziera, Henning Müller, Meritxell Bach Cuadra
Medical Image Segmentation Inherent Interpretability Uncertainty Quantification High Uncertainty Anticipation Lesion Segmentation Multiple Sclerosis Brain Lesion Instance Wise Uncertainty

July 4, 2024

Learning Interpretable Differentiable Logic Networks
Chang Yue, Niraj K. Jha
Inherent Interpretability Gradient Based Differentiable Logic

July 3, 2024

RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring
Ali Ghiasvand Mohammadkhani
Large Language Model Language Model Inherent Interpretability Complex Reasoning Score Distillation Essay Scoring Reasoning Distillation

July 2, 2024

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, Ziyu Yao
Inherent Interpretability DCU Insight AQ Transformer Based Language Model Neural Network Model Mechanistic Interpretability

Inherent Interpretability

Papers

Network Inversion of Convolutional Neural Nets

A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models

Refining Tuberculosis Detection in CXR Imaging: Addressing Bias in Deep Neural Networks via Interpretability

Semantic Prototypes: Enhancing Transparency Without Black Boxes

Why do you cite? An investigation on citation intents and decision-making classification processes

CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis

A survey and taxonomy of methods interpreting random forest models

Explaining Deep Neural Networks by Leveraging Intrinsic Methods

Are Linear Regression Models White Box and Interpretable?

Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent

Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions

Generally-Occurring Model Change for Robust Counterfactual Explanations

Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations

Integrating White and Black Box Techniques for Interpretable Machine Learning

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort

Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis

Learning Interpretable Differentiable Logic Networks

RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models