 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from May 4, 2023 (UTC)
|
| 1. | Distilling Step-by-Step Outperforming Larger Language Models with Less Training (arxiv.org) |
| 153 points by verdverm on May 4, 2023 | hide | past | pdf | 34 comments | |
| 2. | Unlimiformer: Long-Range Transformers with Unlimited Length Input (arxiv.org) |
| 3 points by jasondavies on May 4, 2023 | hide | past | pdf | 3 comments | |
| 3. | An Archaeology of Books Known to ChatGPT/GPT-4 (arxiv.org) |
| 3 points by belter on May 4, 2023 | hide | past | pdf | 1 comment | |
| 4. | Finding Neurons in a Haystack: Case Studies with Sparse Probing (arxiv.org) |
| 2 points by tim_sw on May 4, 2023 | hide | past | pdf | discuss | |