Zobrazeno 1 - 10
of 1 431
pro vyhledávání: '"Saparov AS"'
Autor:
Saparov, Abulhair, Pawar, Srushti, Pimpalgaonkar, Shreyas, Joshi, Nitish, Pang, Richard Yuanzhe, Padmakumar, Vishakh, Kazemi, Seyed Mehran, Kim, Najoung, He, He
Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient model paramete
Externí odkaz:
http://arxiv.org/abs/2412.04703
Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to problems that are more complex than the ones on which they have been trained. Empirical investigations of such q
Externí odkaz:
http://arxiv.org/abs/2410.13502
Phonon nonreciprocity, indicating different transport properties along opposite directions, has been observed in experiments under a magnetic field. We show that nonreciprocal acoustic phonons can also exist without a magnetic field nor net magnetiza
Externí odkaz:
http://arxiv.org/abs/2407.09361
Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transfor
Externí odkaz:
http://arxiv.org/abs/2407.02646
Recent work shows that causal facts can be effectively extracted from LLMs through prompting, facilitating the creation of causal graphs for causal inference tasks. However, it is unclear if this success is limited to explicitly-mentioned causal fact
Externí odkaz:
http://arxiv.org/abs/2406.12158
Autor:
Kurmukov, Anvar, Chernina, Valeria, Gareeva, Regina, Dugova, Maria, Petrash, Ekaterina, Aleshina, Olga, Pisov, Maxim, Shirokikh, Boris, Samokhin, Valentin, Proskurov, Vladislav, Shimovolos, Stanislav, Basova, Maria, Goncahrov, Mikhail, Soboleva, Eugenia, Donskova, Maria, Yaushev, Farukh, Shevtsov, Alexey, Zakharov, Alexey, Saparov, Talgat, Gombolevskiy, Victor, Belyaev, Mikhail
Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA on the ti
Externí odkaz:
http://arxiv.org/abs/2406.08137
Autor:
Anwar, Usman, Saparov, Abulhair, Rando, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Lubana, Ekdeep Singh, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L., Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi, Zhong, Ruiqi, hÉigeartaigh, Seán Ó, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Petrov, Aleksandar, de Witt, Christian Schroeder, Motwan, Sumeet Ramesh, Bengio, Yoshua, Chen, Danqi, Torr, Philip H. S., Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob, Tramer, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods
Externí odkaz:
http://arxiv.org/abs/2404.09932
Autor:
Opedal, Andreas, Stolfo, Alessandro, Shirakami, Haruki, Jiao, Ying, Cotterell, Ryan, Schölkopf, Bernhard, Saparov, Abulhair, Sachan, Mrinmaya
There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which properties of human cognition are well-modeled by LLMs, and which are not. In this work, we study the bia
Externí odkaz:
http://arxiv.org/abs/2401.18070
Autor:
Sourabh, S., Afshari, H., Whiteside, V. R., Eperon, G. E., Scheidt, R. A., Creason, T. D., Furis, M., Kirmani, A., Saparov, B., Luther, J. M., Beard, M. C., Sellers, I. R.
The presence of hot carriers is presented in the operational properties of an (FA,Cs)Pb(I, Br, Cl)3 solar cell at ambient temperatures and under practical solar concentration. At 100 K, clear evidence of hot carriers is observed in both the high ener
Externí odkaz:
http://arxiv.org/abs/2311.08294
Autor:
Zheng, Hongyi, Saparov, Abulhair
Recent advances in prompt engineering enable large language models (LLMs) to solve multi-hop logical reasoning problems with impressive accuracy. However, there is little existing work investigating the robustness of LLMs with few-shot prompting tech
Externí odkaz:
http://arxiv.org/abs/2311.00258