生成式人工智能的算法伦理难点分析与探索
"模型可解释性" 相关文章
Anthropic’s Evaluation of Chain-of-Thought Faithfulness: Investigating Hidden Reasoning, Reward Hacks, and the Limitations of Verbal AI Transparency in Reasoning Models
This AI Paper Introduces a Short KL+MSE Fine-Tuning Strategy: A Low-Cost Alternative to End-to-End Sparse Autoencoder Training for Interpretability
AI日报 - 2025年4月2日
Anthropic CEO Dario Amodei warns of ‘race’ to understand AI as it becomes more powerful
Visualizing Interpretability
Training Data Attribution (TDA):
Examining Its Adoption & Use Cases
AIhub monthly digest: November 2024 – dynamic faceted search, the kidney exchange problem, and AfriClimate AI
AXRP Episode 38.2 - Jesse Hoogland on Singular Learning Theory
Using Uncertainty to Interpret your Model
做出最好大模型的 CEO，不认为 Scaling Law 撞墙了
How to Explain the Prediction of a Machine Learning Model?
SAEs are highly dataset dependent: a case study on the refusal direction
Refined Local Learning Coefficients (rLLCs): A Novel Machine Learning Approach to Understanding the Development of Attention Heads in Transformers
Exploring Input Space Mode Connectivity: Insights into Adversarial Detection and Deep Neural Network Interpretability
Let's Decrypt Dot by Dot: Decoding Hidden Computation in Transformer Language Models
链式思考如何激发大模型算术推理能力？科学家从神经元激活角度给出答案
Gemma 2-2B Released: A 2.6 Billion Parameter Model Offering Advanced Text Generation, On-Device Deployment, and Enhanced Safety Features
Legal and Policy Implications of Model Interpretability with Solon Barocas - TWiML Talk #219
AI for High-Stakes Decision Making with Hima Lakkaraju - #387
