Steering Without Side Effects: Improving Post-Deployment Control of Language Models von Stickland, Asa Cooper, Lyzhov, Alexander, Pfau, Jacob, Mahdi, Salsabila, Bowman, Samuel R

Volltext bestellen

Debate Helps Supervise Unreliable Experts von Michael, Julian, Mahdi, Salsabila, Rein, David, Petty, Jackson, Dirani, Julien, Padmakumar, Vishakh, Bowman, Samuel R

Volltext bestellen

Steering Without Side Effects: Improving Post-Deployment Control of Language Models von Asa Cooper Stickland, Lyzhov, Alexander, Pfau, Jacob, Salsabila Mahdi, Bowman, Samuel R

Volltext

Debate Helps Supervise Unreliable Experts von Julian, Michael, Salsabila Mahdi, Rein, David, Petty, Jackson, Dirani, Julien, Padmakumar, Vishakh, Bowman, Samuel R

Volltext

A 2019-2020 Review of R Neural Network Packages with NNbenchmark von Mahdi, Salsabila, Verma, Akshaj, Dutang, Christophe, Kiener, Patrice, Nash, John C.

Volltext bestellen