Can Models be Evaluation Aware Without Explicit Verbalization?
"interpretability" 相关文章
Bottom-Up: Principled Compression to Shrink LLMs
Toward Statistical Mechanics Of Interfaces Under Selection Pressure
【ICML25】使用信息瓶颈理论为点云模型进行错误归因，为安全问题构建可解释工具
The Future of Interpretability is Geometric
Learning to Interpret Weight Differences in Language Models
Activation Plateaus: Where and How They Emerge
Activation Plateaus: Where and How They Emerge
Finding Features in Neural Networks with the Empirical NTK
大语言模型的遗忘也许是一个悖论？清华团队揭示Unlearning技术的两难困境
Training Qwen-1.5B with a CoT legibility penalty
Training Qwen-1.5B with a CoT legibility penalty
Investigating Neural Scaling Laws Emerging from Deep Data Structure
Experience Report - ML4Good Bootcamp Singapore, Sep'25
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
这次，LLM黑盒被LLM打开了~
这次，LLM黑盒被LLM打开了~
Synthesizing Standalone World-Models, Part 4: Metaphysical Justifications
清华团队提出药物相互作用预测方法，预测准确率提升近三成
当AI学会欺骗，我们该如何应对？
