Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Authors: Che, Zora, Casper, Stephen, Kirk, Robert, Satheesh, Anirudh, Slocum, Stewart, McKinney, Lev E, Gandikota, Rohit, Ewart, Aidan, Rosati, Domenic, Wu, Zichu, Cai, Zikui, Chughtai, Bilal, Gal, Yarin, Huang, Furong, Hadfield-Menell, Dylan

Subject Terms: Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2502.05209

The AI Agent Index

Authors: Casper, Stephen, Bailey, Luke, Hunter, Rosco, Ezell, Carson, Cabalé, Emma, Gerovitch, Michael, Slocum, Stewart, Wei, Kevin, Jurkovic, Nikola, Khan, Ariba, Christoffersen, Phillip J. K., Ozisik, A. Pinar, Trivedi, Rakshit, Hadfield-Menell, Dylan, Kolt, Noam

Subject Terms: Computer Science - Software Engineering, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2502.01635

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Authors: Casper, Stephen, Davies, Xander, Shi, Claudia, Gilbert, Thomas Krendl, Scheurer, Jérémy, Rando, Javier, Freedman, Rachel, Korbak, Tomasz, Lindner, David, Freire, Pedro, Wang, Tony, Marks, Samuel, Segerie, Charbel-Raphaël, Carroll, Micah, Peng, Andi, Christoffersen, Phillip, Damani, Mehul, Slocum, Stewart, Anwar, Usman, Siththaranjan, Anand, Nadeau, Max, Michaud, Eric J., Pfau, Jacob, Krasheninnikov, Dmitrii, Chen, Xin, Langosco, Lauro, Hase, Peter, Bıyık, Erdem, Dragan, Anca, Krueger, David, Sadigh, Dorsa, Hadfield-Menell, Dylan

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2307.15217

Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Authors: Chattopadhyay, Aditya, Slocum, Stewart, Haeffele, Benjamin D., Vidal, Rene, Geman, Donald

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2207.00938

Disks in Nearby Young Stellar Associations Found Via Virtual Reality

Authors: Higashio, Susan, Kuchner, Marc J., Silverberg, Steven M., Brandt, Matthew A., Grubb, Thomas G., Gagné, Jonathan, Debes, John H., Schlieder, Joshua, Wisniewski, John P., Slocum, Stewart, Bans, Alissa S., Bhattacharjee, Shambo, Biggs, Joseph R., Bosch, Milton K. D., Cernohous, Tadeas, Doll, Katharina, Luca, Hugo A. Durantini, Enachioaie, Alexandru, Griffith Sr., Phillip, Hamilton, Joshua, Holden, Jonathan, Hyogo, Michiharu, Jung, Dawoon, Lau, Lily, Piipuu, Fernanda Piñiero Art, Stiller, Lisa, Collaboration, Disk Detective

Subject Terms: Astrophysics - Solar and Stellar Astrophysics, Astrophysics - Earth and Planetary Astrophysics

Access URL: http://arxiv.org/abs/2205.09133

Socratic Artificial Intelligence Learning (SAIL): The Role of a Virtual Voice Assistant in Learning Orthopedic Knowledge

Authors: Li, Tuo Peter, Slocum, Stewart, Sahoo, Arpan, Ochuba, Arinze, Kolakowski, Logan, Henn III, Ralph Frank, Johnson, Alex A., LaPorte, Dawn M.

Source: In Journal of Surgical Education November 2024 81(11):1655-1666

AdaLead: A simple and robust adaptive greedy search algorithm for sequence design

Authors: Sinai, Sam, Wang, Richard, Whatley, Alexander, Slocum, Stewart, Locane, Elina, Kelsic, Eric D.

Subject Terms: Computer Science - Machine Learning, Mathematics - Optimization and Control, Quantitative Biology - Biomolecules, Quantitative Biology - Quantitative Methods

Access URL: http://arxiv.org/abs/2010.02141

Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Authors: Chattopadhyay, Aditya, Slocum, Stewart, Haeffele, Benjamin D., Vidal, Rene, Geman, Donald

Source: IEEE Transactions on Pattern Analysis and Machine Intelligence; 2023, Vol. 45 Issue: 6 p7430-7443, 14p