 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from August 29, 2023 (UTC)
|
| 1. | Reinforced Self-Training (ReST) for Language Modeling (arxiv.org) |
| 13 points by jonbaer on Aug 29, 2023 | hide | past | pdf | 1 comment | |
| 2. | Traffic Light Control with Reinforcement Learning (arxiv.org) |
| 5 points by diogotozzi on Aug 29, 2023 | hide | past | pdf | discuss | |
| 3. | Halo: Estimation and Reduction of Hallucinations in Open-Source Weak LLMs (arxiv.org) |
| 3 points by PaulHoule on Aug 29, 2023 | hide | past | pdf | discuss | |
| 4. | Are ChatGPT and GPT-4 Good Poker Players? – A Pre-Flop Analysis (arxiv.org) |
| 2 points by PaulHoule on Aug 29, 2023 | hide | past | pdf | 1 comment | |
| 5. | Detecting Language Model Attacks with Perplexity (arxiv.org) |
| 1 point by diogotozzi on Aug 29, 2023 | hide | past | pdf | discuss | |
| 6. | The Poison of Alignment (arxiv.org) |
| 1 point by goat-zero on Aug 29, 2023 | hide | past | pdf | 1 comment | |