 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from December 12, 2024 (UTC)
|
| 1. | Frontier Models are Capable of In-context Scheming (arxiv.org) |
| 10 points by trott on Dec 12, 2024 | hide | past | pdf | 1 comment | |
| 2. | Forking Paths in Neural Text Generation (arxiv.org) |
| 2 points by pizza on Dec 12, 2024 | hide | past | pdf | discuss | |
| 3. | LLM-Take: Theme-Aware Keyword Extraction Using Large Language Models (arxiv.org) |
| 1 point by klaussilveira on Dec 12, 2024 | hide | past | pdf | discuss | |
| 4. | Antelope: Potent and Concealed Jailbreak Attack Strategy (arxiv.org) |
| 1 point by belter on Dec 12, 2024 | hide | past | pdf | discuss | |
| 5. | Understanding Hidden Computations in Chain-of-Thought Reasoning (arxiv.org) |
| 1 point by riemann77 on Dec 12, 2024 | hide | past | pdf | 1 comment | |