| Emergent LLM behaviors are observationally equivalent to data leakage | May 26, 2025 | Memorization | CodeCode Available | 0 |
| Spurious Privacy Leakage in Neural Networks | May 26, 2025 | Memorization | —Unverified | 0 |
| Grokking ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior | May 26, 2025 | AttributeMemorization | CodeCode Available | 0 |
| Understanding Generalization in Diffusion Models via Probability Flow Distance | May 26, 2025 | Memorization | —Unverified | 0 |
| Querying Kernel Methods Suffices for Reconstructing their Training Data | May 25, 2025 | Density EstimationMemorization | CodeCode Available | 0 |
| Discovering Forbidden Topics in Language Models | May 23, 2025 | Memorization | —Unverified | 0 |
| Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training | May 23, 2025 | Memorization | —Unverified | 0 |
| Memorization or Reasoning? Exploring the Idiom Understanding of LLMs | May 22, 2025 | Machine TranslationMemorization | —Unverified | 0 |
| Sudoku-Bench: Evaluating creative reasoning with Sudoku variants | May 22, 2025 | DiversityLogical Reasoning | CodeCode Available | 0 |
| Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge | May 22, 2025 | Memorization | —Unverified | 0 |
