|
|
|
Stories from June 7, 2023 (UTC)
|
| 1. |
I'm afraid I can't do that: Prompt refusal in generative language models (arxiv.org) |
|
179 points by belter on Jun 7, 2023 | hide | past | pdf | 166 comments
|
|
| 2. |
CodeTF: One-Stop Transformer Library for State-of-the-Art Code LLM (arxiv.org) |
|
95 points by pabo on Jun 7, 2023 | hide | past | pdf | 6 comments
|
|
| 3. |
Orca: Progressive Learning from Complex Explanation Traces of GPT-4 (arxiv.org) |
|
11 points by huijzer on Jun 7, 2023 | hide | past | pdf | 3 comments
|
|
| 4. |
Towards Revealing the Mystery Behind Chain of Thought: A Theoretical Perspective (arxiv.org) |
|
5 points by krackers on Jun 7, 2023 | hide | past | pdf | 1 comment
|
|
| 5. |
Leace: Perfect linear concept erasure in closed form (arxiv.org) |
|
5 points by anigbrowl on Jun 7, 2023 | hide | past | pdf | 1 comment
|
|
| 6. |
Free-Lunch Explainability for DL Architectures (arxiv.org) |
|
4 points by pfnguy on Jun 7, 2023 | hide | past | pdf | discuss
|
|
| 7. |
A Constraint Programming Solver Guided by Reinforcement Learning (2021) (arxiv.org) |
|
3 points by yeesian on Jun 7, 2023 | hide | past | pdf | 1 comment
|
|
| 8. |
SAIL: Search-Augmented Instruction Learning (arxiv.org) |
|
2 points by rntn on Jun 7, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Human or Not? A Gamified Approach to the Turing Test (arxiv.org) |
|
2 points by isaacfrond on Jun 7, 2023 | hide | past | pdf | 1 comment
|
|
| 10. |
Combinatorial optimization and reasoning with graph neural networks (2022) (arxiv.org) |
|
2 points by yeesian on Jun 7, 2023 | hide | past | pdf | discuss
|
|
| 11. |
Learning Transformer Programs (arxiv.org) |
|
1 point by yeesian on Jun 7, 2023 | hide | past | pdf | discuss
|
|
| 12. |
Large Language Models of Code Fail at Completing Code with Potential Bugs (arxiv.org) |
|
1 point by 0xedb on Jun 7, 2023 | hide | past | pdf | discuss
|
|
|
|
