side effect
- Oceania > Australia > Victoria > Melbourne (0.04)
- North America > United States > Colorado (0.04)
- North America > United States > Arizona (0.04)
- (4 more...)
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.68)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (0.67)
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.14)
- North America > United States > California > San Francisco County > San Francisco (0.14)
- North America > United States > New York > New York County > New York City (0.04)
- (4 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Constraint-Based Reasoning (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Inductive Learning (0.67)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Asia > Middle East > Jordan (0.04)
FDA Approves Pill Version of Wegovy
Novo Nordisk's semaglutide will soon be available in a daily pill Americans can take for weight loss. The US Food and Drug Administration today approved a pill version of the blockbuster anti-obesity drug Wegovy. Made by Novo Nordisk, the pill is taken once a day. The company's original version of Wegovy is a weekly injection. Both drugs contain the same active ingredient, semaglutide.
- North America > United States > California (0.05)
- Europe > Slovakia (0.05)
- Europe > Czechia (0.05)
Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
Raimondi, Bianca, Dalbagno, Daniela, Gabbrielli, Maurizio
Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear. In this work, we investigated whether the well-known Knobe effect, a moral bias in intentionality judgements, emerges in finetuned LLMs and whether it can be traced back to specific components of the model. We conducted a Layer-Patching analysis across 3 open-weights LLMs and demonstrated that the bias is not only learned during finetuning but also localized in a specific set of layers. Surprisingly, we found that patching activations from the corresponding pretrained model into just a few critical layers is sufficient to eliminate the effect. Our findings offer new evidence that social biases in LLMs can be interpreted, localized, and mitigated through targeted interventions, without the need for model retraining.
- North America > United States (0.14)
- Europe > Italy > Emilia-Romagna > Metropolitan City of Bologna > Bologna (0.04)
- North America > Canada > Ontario > Toronto (0.04)
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (0.93)
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.14)
- North America > United States > California > San Francisco County > San Francisco (0.14)
- North America > United States > New York > New York County > New York City (0.04)
- (4 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Constraint-Based Reasoning (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Inductive Learning (0.67)
Can one big meal really make you gain weight?
Can one big meal really make you gain weight? The post-holiday scale spike is temporary--unless the leftovers get involved. It's hard not to indulge during the holidays, but can the occasional big meal really harm our long-term health? Breakthroughs, discoveries, and DIY tips sent every weekday. For those of us brave enough to step onto the scale the day after Thanksgiving or Christmas, you can sometimes see an increase of up to five to 10 pounds.
- Health & Medicine > Consumer Health (1.00)
- Health & Medicine > Therapeutic Area > Psychiatry/Psychology (0.34)
- Health & Medicine > Therapeutic Area > Endocrinology (0.34)
- Health & Medicine > Therapeutic Area > Cardiology/Vascular Diseases (0.31)
- North America > United States > California (0.17)
- North America > United States > New Jersey (0.04)
- Health & Medicine > Therapeutic Area > Oncology (1.00)
- Government > Regional Government > North America Government > United States Government > FDA (0.72)