The Generative AI Paradox: "What It Can Create, It May Not Understand"
Paper • 2311.00059 • Published • 18
AI & ML interests
None defined yet.
jenah
authored 14
papers over 1 year ago
Faith and Fate: Limits of Transformers on Compositionality
Paper • 2305.18654 • Published • 9
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Paper • 2305.19472 • Published • 1
UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
Paper • 2311.08469 • Published • 11
SPLAIN: Augmenting Cybersecurity Warnings with Reasons and Data
Paper • 2311.11215 • Published • 2
COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements
Paper • 2306.01985 • Published • 1
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
Paper • 2110.07178 • Published • 1
Can Machines Learn Morality? The Delphi Experiment
Paper • 2110.07574 • Published
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
Paper • 2309.00779 • Published • 2
Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Paper • 2209.06293 • Published • 1
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation
Paper • 2212.09246 • Published
ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
Paper • 2212.10409 • Published
Social Chemistry 101: Learning to Reason about Social and Moral Norms
Paper • 2011.00620 • Published
DataDecide: How to Predict Best Pretraining Data with Small Experiments
Paper • 2504.11393 • Published • 20
jenah
authored a
paper almost 2 years ago