 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from April 19, 2025 (UTC)
|
| 1. | CaMeL: Defeating Prompt Injections by Design (arxiv.org) |
| 71 points by tomrod on Apr 19, 2025 | hide | past | pdf | 16 comments | |
| 2. | Inferring the Phylogeny of Large Language Models (arxiv.org) |
| 69 points by weinzierl on Apr 19, 2025 | hide | past | pdf | 6 comments | |
| 3. | Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents (arxiv.org) |
| 14 points by distalx on Apr 19, 2025 | hide | past | pdf | discuss | |
| 4. | Do Reasoning Models Show Better Verbalized Calibration? (arxiv.org) |
| 2 points by veryluckyxyz on Apr 19, 2025 | hide | past | pdf | discuss | |
| 5. | Defeating Prompt Injections by Design (arxiv.org) |
| 2 points by theptip on Apr 19, 2025 | hide | past | pdf | discuss | |
| 6. | How to evaluate control measures for LLM agents? (arxiv.org) |
| 2 points by handfuloflight on Apr 19, 2025 | hide | past | pdf | discuss | |
| 7. | Using Small Models to Compare Language Learning and Tokenizer Performance (arxiv.org) |
| 1 point by PaulHoule on Apr 19, 2025 | hide | past | pdf | discuss | |