1
Analysis of Information Theory for Explainable AI
用信息论量化AI决策过程，为模型可解释性提供严谨数学框架
arXiv:2507.09092v2 Announce Type: replace-cross Abstract: With the intervention of machine vision in our crucial day to day necessities including heal…
2
Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
用无监督学习揭开亨廷顿病分期之谜，模型表征与聚类分析解读疾病进展规律
arXiv:2606.07135v1 Announce Type: new Abstract: Huntington's disease (HD) is a progressive neurodegenerative disorder that affects motor, cognitive, a…
3
Decomposing how prompting steers behavior
arXiv论文揭秘提示词如何无参数更新地引导模型行为，揭示背后机制
arXiv:2606.03093v1 Announce Type: new Abstract: Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates…
4
Interpreto: An Explainability Library for Transformers
Transformer模型的黑箱问题有了新解法，这个可解释性库帮你看清内部机制
arXiv:2512.09730v3 Announce Type: replace-cross Abstract: Interpreto is an open-source Python library for interpreting HuggingFace language models, fr…
5
Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines
无需纠正即可检测，两参数分解多阶段LLM管道，揭示内部机制新视角
arXiv:2605.27559v1 Announce Type: cross Abstract: Multi-stage LLM pipelines that perform multi-agent debate, intrinsic self-correction, or retrieval-a…
6
Probabilistic Attribution For Large Language Models
利用条件概率解析大模型生成逻辑，揭示训练与推理中的分布结构。
arXiv:2605.21726v1 Announce Type: new Abstract: The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities th…
7
FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision
提出FM-G-CAM新方法，全面解释CNN预测，提升可解释AI在视觉领域的实用性。
arXiv:2312.05975v3 Announce Type: replace-cross Abstract: Explainability is a vital aspect of modern AI for real-world impact and usability. The main …
8
CUBE: Contrastive Understanding by Balanced Experiments
用因子实验设计解释黑盒模型，CUBE框架通过平衡探针组合评估预测器，提供清晰因果效应总结。
arXiv:2509.10825v5 Announce Type: replace-cross Abstract: Explaining a trained model requires a clear account of how explanatory evidence is generated…