explainability
PulseAugur coverage of explainability — every cluster mentioning explainability across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New LLM 'Queen' plays chess at Grandmaster level and explains moves · 4 sources tracked
Researchers have developed a novel framework called Queen, a 4-billion parameter language model that can play chess at a Grandmaster level and explain its moves. This model integrates a silent expert chess encoder with …
-
AI adoption outpaces trust; explainability is key to closing the gap
Businesses are rapidly adopting AI tools and integrating them into critical decision-making processes, but this adoption is outpacing the development of trust in these systems. The gap between AI adoption and trust can …
-
Psychological Trust in AI: Beyond Creator Reputation
Trust in artificial intelligence is a complex issue with multiple facets beyond just the reputation of the AI's creator. Factors such as the AI's explainability, accountability, and the user's experience all play signif…
-
New XCal-FL algorithm enhances explainability in differentially private federated learning
Researchers have developed XCal-FL, a novel federated learning algorithm that dynamically calibrates differential privacy noise to improve explainability. This method addresses the issue where standard differential priv…
-
Review paper details trustworthy AI for digital health
A new review paper published on arXiv synthesizes recent advancements in trustworthy artificial intelligence, focusing specifically on robustness and explainability within the digital health domain. The paper outlines k…
-
New research highlights challenges in AI explainability requirements engineering
A new research paper explores the challenges of integrating explainability requirements into existing Requirements Engineering (RE) practices within the AI domain. The study, which involved eight practitioners at Daimle…
-
Sparse Autoencoders: Promise and Pitfalls in AI Interpretability
Researchers are exploring Sparse Autoencoders (SAEs) for mechanistic interpretability, aiming to uncover distinct concepts within large language models. A new method, Structured Sparse AutoEncoder ($S^2AE$), improves co…
-
Machine learning interpretability and explainability in physics analyzed
This paper reviews the concepts of interpretability and explainability within the context of machine learning applied to physics. It defines interpretability as the structural transparency of a model and explainability …
-
Themis framework combines AI explainability with human feedback for safer RL
Researchers have introduced Themis, a novel framework designed to enhance the safety and transparency of Reinforcement Learning (RL) systems by integrating explainability with human feedback. This framework aims to addr…
-
New metric quantifies AI explanation fragility in cybersecurity
This paper introduces a novel metric, the Explanability Fragility Score, to quantify instability in AI explanations within cybersecurity intrusion detection systems. The research demonstrates that multicollinearity, a s…