| Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers | Jul 16, 2024 | Memorization | CodeCode Available | 0 |
| Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment | Jul 15, 2024 | Domain AdaptationMemorization | —Unverified | 0 |
| Extracting Training Data from Document-Based VQA Models | Jul 11, 2024 | MemorizationQuestion Answering | —Unverified | 0 |
| MUSE: Machine Unlearning Six-Way Evaluation for Language Models | Jul 8, 2024 | ArticlesMachine Unlearning | CodeCode Available | 4 |
| UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization | Jul 3, 2024 | MemorizationQuestion Answering | —Unverified | 0 |
| PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding | Jul 3, 2024 | Memorization | —Unverified | 0 |
| Towards More Realistic Extraction Attacks: An Adversarial Perspective | Jul 2, 2024 | Memorization | CodeCode Available | 0 |
| Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning | Jul 1, 2024 | Memorization | CodeCode Available | 1 |
| We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? | Jul 1, 2024 | MathMathematical Reasoning | CodeCode Available | 2 |
| Detection and Measurement of Syntactic Templates in Generated Text | Jun 28, 2024 | DiversityMemorization | —Unverified | 0 |
