Cover Image

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	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
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909307172290560
author	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
author_facet	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
contents	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, and sociotechnical challenges. Based on the identified challenges, we pose $200+$ concrete research questions.
format	Preprint
id	arxiv_https___arxiv_org_abs_2404_09932
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Foundational Challenges in Assuring Alignment and Safety of Large Language Models 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 Machine Learning Artificial Intelligence Computation and Language Computers and Society 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, and sociotechnical challenges. Based on the identified challenges, we pose $200+$ concrete research questions.
title	Foundational Challenges in Assuring Alignment and Safety of Large Language Models
topic	Machine Learning Artificial Intelligence Computation and Language Computers and Society
url	https://arxiv.org/abs/2404.09932