Zobrazeno 1 - 10
of 2 925
pro vyhledávání: '"Shaw, Peter"'
Following natural language instructions by executing actions in digital environments (e.g. web-browsers and REST APIs) is a challenging task for language model (LM) agents. Unfortunately, LM agents often fail to generalize to new environments without
Externí odkaz:
http://arxiv.org/abs/2403.08140
Autor:
Eisenstein, Jacob, Nagpal, Chirag, Agarwal, Alekh, Beirami, Ahmad, D'Amour, Alex, Dvijotham, DJ, Fisch, Adam, Heller, Katherine, Pfohl, Stephen, Ramachandran, Deepak, Shaw, Peter, Berant, Jonathan
Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a phenomenon ofte
Externí odkaz:
http://arxiv.org/abs/2312.09244
Autor:
Shaw, Peter, Joshi, Mandar, Cohan, James, Berant, Jonathan, Pasupat, Panupong, Hu, Hexiang, Khandelwal, Urvashi, Lee, Kenton, Toutanova, Kristina
Much of the previous work towards digital agents for graphical user interfaces (GUIs) has relied on text-based representations (derived from HTML or other structured data sources), which are not always readily available. These input representations h
Externí odkaz:
http://arxiv.org/abs/2306.00245