|
|
|
Stories from November 15, 2023 (UTC)
|
| 1. |
Beyond Memorization: Violating privacy via inference with LLMs (arxiv.org) |
|
127 points by vissidarte_choi on Nov 15, 2023 | hide | past | pdf | 80 comments
|
|
| 2. |
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module (arxiv.org) |
|
8 points by mromanuk on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 3. |
Large Language Models Can Strategically Deceive Their Users When Under Pressure (arxiv.org) |
|
8 points by Jimmc414 on Nov 15, 2023 | hide | past | pdf | 2 comments
|
|
| 4. |
A Watermark for Large Language Models (arxiv.org) |
|
3 points by EndXA on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 5. |
Ghostbuster: Detecting Text Ghostwritten by Large Language Models (arxiv.org) |
|
2 points by josh-sematic on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 6. |
Do Large Language Models Know What They Don't Know? (arxiv.org) |
|
2 points by wseqyrku on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 7. |
Mart: Improving LLM Safety with Multi-Round Automatic Red-Teaming (arxiv.org) |
|
1 point by georgehill on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 8. |
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents (arxiv.org) |
|
1 point by muggermuch on Nov 15, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Large Language Models Can Strategically Deceive Their Users When Under Pressure (arxiv.org) |
|
1 point by famouswaffles on Nov 15, 2023 | hide | past | pdf | 1 comment
|
|
| 10. |
Demasq: Unmasking the ChatGPT Wordsmith (arxiv.org) |
|
1 point by PaulHoule on Nov 15, 2023 | hide | past | pdf | 1 comment
|
|
|
|
