Concept-Oriented Deep Learning with Large Language Models
Paper
•
2306.17089
•
Published
•
1
Concept
-
-
Extracting Mathematical Concepts with Large Language Models
Paper • 2309.00642 • Published • 1 -
An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning
Paper • 2310.12274 • Published • 11 -
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models
Paper • 2211.04079 • Published • 1 -
The Linear Representation Hypothesis and the Geometry of Large Language Models
Paper • 2311.03658 • Published • 1 -
Interpreting Pretrained Language Models via Concept Bottlenecks
Paper • 2311.05014 • Published • 1 -
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Paper • 2306.12672 • Published • 26 -
Identifying Linear Relational Concepts in Large Language Models
Paper • 2311.08968 • Published • 1 -
Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace
Paper • 2305.15775 • Published • 1 -
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
Paper • 2311.08648 • Published • 2 -
FACT: Learning Governing Abstractions Behind Integer Sequences
Paper • 2209.09543 • Published • 2 -
Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?
Paper • 2304.01083 • Published • 1 -
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
Paper • 2311.04335 • Published • 1 -
Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
Paper • 2302.09582 • Published • 1 -
Graph schemas as abstractions for transfer learning, inference, and planning
Paper • 2302.07350 • Published • 1