Papers by Maurice Pagnucco
Temporal Alignment of Time Sensitive Facts with Activation Engineering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models are trained on diverse and conflicting knowledge spanning multiple domains and time periods. |
| Approach: | They propose a method for temporally aligning large language models to improve factual recall without training. |
| Outcome: | The proposed method improves factual recall without training. |