Research Areas in Interpretability (The Alignment Project by UK AISI)
"可解释性" 相关文章
Unifying Post-hoc Explanations of Knowledge Graph Completions
RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment
On Explaining Visual Captioning with Hybrid Markov Logic Networks
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
LLM-Adapted Interpretation Framework for Machine Learning Models
Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
Unlocking Interpretability for RF Sensing: A Complex-Valued White-Box Transformer
Deliberative Credit Assignment (DCA): Making Faithful Reasoning Profitable
Shapley-Value-Based Graph Sparsification for GNN Inference
On the Limits of Hierarchically Embedded Logic in Classical Neural Networks
Compositional Function Networks: A High-Performance Alternative to Deep Neural Networks with Built-in Interpretability
Concept Learning for Cooperative Multi-Agent Reinforcement Learning
Studying Cross-cluster Modularity in Neural Networks
SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
大模型上下文学习的统计物理视角丨周四直播·大模型可解释性读书会
大模型上下文学习的统计物理视角丨周四直播·大模型可解释性读书会
Explainable Graph Neural Networks via Structural Externalities
Pragmatic Policy Development via Interpretable Behavior Cloning
AI Safety x Physics Grand Challenge
