Alert button
Picture for Collin Burns

Collin Burns

Alert button

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Dec 14, 2023
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeff Wu

Viaarxiv icon

Discovering Latent Knowledge in Language Models Without Supervision

Dec 07, 2022
Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt

Figure 1 for Discovering Latent Knowledge in Language Models Without Supervision
Figure 2 for Discovering Latent Knowledge in Language Models Without Supervision
Figure 3 for Discovering Latent Knowledge in Language Models Without Supervision
Figure 4 for Discovering Latent Knowledge in Language Models Without Supervision
Viaarxiv icon

Measuring Coding Challenge Competence With APPS

May 27, 2021
Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt

Figure 1 for Measuring Coding Challenge Competence With APPS
Figure 2 for Measuring Coding Challenge Competence With APPS
Figure 3 for Measuring Coding Challenge Competence With APPS
Figure 4 for Measuring Coding Challenge Competence With APPS
Viaarxiv icon

CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review

Mar 10, 2021
Dan Hendrycks, Collin Burns, Anya Chen, Spencer Ball

Figure 1 for CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Figure 2 for CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Figure 3 for CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Figure 4 for CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Viaarxiv icon

Limitations of Post-Hoc Feature Alignment for Robustness

Mar 10, 2021
Collin Burns, Jacob Steinhardt

Figure 1 for Limitations of Post-Hoc Feature Alignment for Robustness
Figure 2 for Limitations of Post-Hoc Feature Alignment for Robustness
Figure 3 for Limitations of Post-Hoc Feature Alignment for Robustness
Figure 4 for Limitations of Post-Hoc Feature Alignment for Robustness
Viaarxiv icon

Measuring Mathematical Problem Solving With the MATH Dataset

Mar 05, 2021
Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, Jacob Steinhardt

Figure 1 for Measuring Mathematical Problem Solving With the MATH Dataset
Figure 2 for Measuring Mathematical Problem Solving With the MATH Dataset
Figure 3 for Measuring Mathematical Problem Solving With the MATH Dataset
Figure 4 for Measuring Mathematical Problem Solving With the MATH Dataset
Viaarxiv icon

Measuring Massive Multitask Language Understanding

Sep 21, 2020
Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt

Figure 1 for Measuring Massive Multitask Language Understanding
Figure 2 for Measuring Massive Multitask Language Understanding
Figure 3 for Measuring Massive Multitask Language Understanding
Figure 4 for Measuring Massive Multitask Language Understanding
Viaarxiv icon

Aligning AI With Shared Human Values

Aug 05, 2020
Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, Jacob Steinhardt

Figure 1 for Aligning AI With Shared Human Values
Figure 2 for Aligning AI With Shared Human Values
Figure 3 for Aligning AI With Shared Human Values
Figure 4 for Aligning AI With Shared Human Values
Viaarxiv icon