Several readers of Spill the GPTea have reached out to me and requested more explanations of research. In this special edition, you can catch up on the recent research in Explainable AI by reading, listening to, and watching artifacts we have put together for the fall section of Emerging Trends in Explainable AI (see course trailer here).
Creative works
A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME (Salih et al) -
“Lifting the Mask” - Song by Günel Aghakishiyeva:
Red Teaming Language Models with Language Models (Perez, et.al.)
Comic by Vishnu Mukundan Thanikunathe Manoj:
When Explainability Turns into a Threat: Using xAI to Fool a Fake News Detection Method (Kozik, et.al.)
Children’s Storybook by Afraa Noureen (and GitHub explanation):
Written works (Blogs, Websites)
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats (Schwinn, et.al.)
SITUATIONAL AWARENESS: The Decade Ahead (Leopold Aschenbrenner)
Notion Site + Mind Map by Anastasiia Saenko
Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends (Ucar, et.al.)
Code Demonstrations
Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior (Boggust, et.al.)
A Comprehensive Approach to Explainable AI: SHAP's Role in Modern Machine Learning (Baek, et.al.)
Videos
Advancing Explainable AI Toward Human-Like Intelligence: Forging the Path to Artificial Brain (Zhou and Jiang et al)
Video by Osama Ahmed:
Beyond Preferences in AI Alignment (Zhi-Xuan, et.al.)
Video by Ahmed Boutar: https://www.canva.com/design/DAGPwI2cFrA/bLTcg0410TzXLZKoeZ1spA/view?utm_content=DAGPwI2cFrA&utm_campaign=designshare&utm_medium=link&utm_source=recording_view
Explainability pitfalls: Beyond dark patterns in explainable AI (Ehsan, et.al.)
Video by Bob Zhang:
Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy (Pellano, et.al.)
Video by Daniela Jimenez Lara:
https://www.tiktok.com/t/ZP8JbjcAf/
Increasing the value for XAI for users: A Psychology Perspective (Hoffman, et.al.)
Video by Aarya Desai:
From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation (Achtibat, et.al.)
Video by Tina Yi:
Patient Reidentification from Chest Radiographs: An Interpretable Deep Metric Learning Approach and Its Applications (Macpherson, et.al.)
Video by Chad Miller:
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors (Pinhasov, et.al.)
Video by Aryan Laxman Sirohi:
The EU AI Act: National Security Implications (Alan Turing Institute)
Video by Vihaan Nama: https://drive.google.com/file/d/1yZDUBNiTlq9szSDSHaxp3fpwe3K8to7E/view
A multimodal automated interpretability agent (Shaham, et.al.)
Video by Ritu Toshniwal:
Notions of Explainability and Evaluation Approaches for Explainable Artificial Intelligence (Vilone and Longo et al)
Video by Keese Phillips:
Kolmogorov-Arnold Networks (Liu, et.al.)
Video by Yancey Yang:
Identifying drivers and mitigators for congestion and redispatch in the German electric power system with explainable AI (Titz, et.al.)
Video by Rakeen Rouf:
Finding the Right XAI Method - A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science (Bommer, et.al.)
Video by Stuart Bladon:
Explainable Artificial Intelligence Improves Human Decision-Making: Results from a Mushroom Picking Experiment at a Public Art Festival (Leichtmann, et.al.)
Video by Akhil Chintalapati:
Neural Prototype Trees for Explainable and Interpretable Fine-grained Image Recognition (Nauta, et.al.)
Video by Akalpit Dawkhar: https://drive.google.com/file/d/1C7SeQxcElrlVFtkKnbWns3zVYyVyT9of/view?usp=share_link
Evaluating State-of-the-Art Concept-Based XAI Methods in the Extraction of Meaningful Information from Oral Cancer Data (Ekstedt, et.al.)
Video by Tal Erez:
Presentation of Employing Explainable AI to Optimize the Return Target Function of a Loan Portfolio (Gramespacher, et.al.)
Video by Haodong He:
Explainable ML in image classification models: An uncertainty
Video by Shuaiming Jing:
Explainable Spatial-Temporal Graph Neural Networks
Video by Hongxuan (Leo) Li:
An explainable AI (XAI) model for landslide susceptibility modeling (Prodhan, et.al.)
Video by Yabei Zeng:
Interpretable Machine Learning for Discovery: Statistical Challenges and Opportunities
Video by Kelly Tong:
Intrinsic and Post-Hoc XAI Approaches for Fingerprint Identification and Response Prediction in Smart Manufacturing Processes (Madathil, et.al.)
Video by Jinyoung Suh:
What’s meant by explainable model: A Scoping Review (Mainali, et.al.)
Video by Nick Shao: https://drive.google.com/file/d/13GRmKzMN7sDnhyt5uiASdO9XozCiyYIt/view