Filter papers
Remove All Filters
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Reasoning
Pre-Training
Data
Interpretability
Reasoning
Pre-Training
Data
Interpretability
LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives
Generative Models
Language
Tooling
Interpretability
Transformers
Supervised Learning
Open Source
Generative Models
Language
Tooling
Interpretability
Transformers
Supervised Learning
Open Source
The Presidio Recommendations on Responsible Generative AI - World Economic Forum
Interpretability
Safety
Responsible AI
AI Policy
Interpretability
Safety
Responsible AI
AI Policy
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Safety
Reasoning
Interpretability
Safety
Reasoning
Interpretability
Large Language Models are not Zero Shot Communicators
Interpretability
Language
Generative Models
Interpretability
Language
Generative Models
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Efficiency
Interpretability
Safety
Responsible AI
Computer Vision
Efficiency
Interpretability
Safety
Responsible AI
Computer Vision
Robust Distillation for Worst-class Performance
Efficiency
Interpretability
Safety
Responsible AI
Efficiency
Interpretability
Safety
Responsible AI
Predicting Twitter Engagement With Deep Language Models
Generative Models
Interpretability
Generative Models
Interpretability