|
|
|
Stories from June 14, 2025 (UTC)
|
| 1. |
Unsupervised Elicitation of Language Models (arxiv.org) |
|
135 points by kordlessagain on Jun 14, 2025 | hide | past | pdf | 24 comments
|
|
| 2. |
Clinical knowledge in LLMs does not translate to human interactions (arxiv.org) |
|
102 points by insistent on Jun 14, 2025 | hide | past | pdf | 39 comments
|
|
| 3. |
Rethinking Losses for Diffusion Bridge Samplers (arxiv.org) |
|
10 points by badmonster on Jun 14, 2025 | hide | past | pdf | 1 comment
|
|
| 4. |
Comment on the Illusion of Thinking (arxiv.org) |
|
4 points by esafak on Jun 14, 2025 | hide | past | pdf | 1 comment
|
|
| 5. |
Exploring the Best Input Representation for Electrocardiogram-Language Models (arxiv.org) |
|
2 points by PaulHoule on Jun 14, 2025 | hide | past | pdf | discuss
|
|
| 6. |
Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques (arxiv.org) |
|
1 point by codelion on Jun 14, 2025 | hide | past | pdf | discuss
|
|
| 7. |
Relic: Evaluating Compositional Instruction Following via Language Recognition (arxiv.org) |
|
1 point by demirbey05 on Jun 14, 2025 | hide | past | pdf | discuss
|
|
| 8. |
Resa: Transparent Reasoning Models via SAEs (arxiv.org) |
|
1 point by Bogdanp on Jun 14, 2025 | hide | past | pdf | discuss
|
|
| 9. |
CRMArena-Pro: LLM Agents Assessed Across Diverse Business Scenarios (arxiv.org) |
|
1 point by felineflock on Jun 14, 2025 | hide | past | pdf | discuss
|
|
| 10. |
Memoir: Lifelong Model Editing with Minimal Overwrite Informed Retention for LLM (arxiv.org) |
|
1 point by dataminer on Jun 14, 2025 | hide | past | pdf | discuss
|
|
|
|
