|
|
|
Stories from May 31, 2023 (UTC)
|
| 1. |
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets (arxiv.org) |
|
13 points by thunderbong on May 31, 2023 | hide | past | pdf | discuss
|
|
| 2. |
Whose Opinions Do Language Models Reflect? (arxiv.org) |
|
4 points by rntn on May 31, 2023 | hide | past | pdf | 1 comment
|
|
| 3. |
Direct Preference Optimization: Your Language Model Is a Reward Model (arxiv.org) |
|
4 points by tim_sw on May 31, 2023 | hide | past | pdf | discuss
|
|
| 4. |
Fine-Tuning Language Models with Just Forward Passes (arxiv.org) |
|
3 points by famouswaffles on May 31, 2023 | hide | past | pdf | 1 comment
|
|
| 5. |
Intriguing Properties of Quantization at Scale (arxiv.org) |
|
2 points by Jimmc414 on May 31, 2023 | hide | past | pdf | discuss
|
|
| 6. |
NetHack Is Hard to Hack (arxiv.org) |
|
2 points by bikenaga on May 31, 2023 | hide | past | pdf | discuss
|
|
| 7. |
WikiChat: A Few-Shot LLM-Based Chatbot Grounded with Wikipedia (arxiv.org) |
|
2 points by gdss on May 31, 2023 | hide | past | pdf | discuss
|
|
| 8. |
Concise Answers to Complex Questions: Summarization of Long-Form Answers (arxiv.org) |
|
1 point by Jimmc414 on May 31, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Outline, Then Details: Syntactically Guided Coarse-to-Fine Code Generation (arxiv.org) |
|
1 point by PaulHoule on May 31, 2023 | hide | past | pdf | discuss
|
|
|
|
