Cite
Notes
Only stored in your browser.
Attribution
Debating with More Persuasive LLMs Leads to More Truthful Answers
arXiv 2024
A Configurable Library for Generating and Manipulating Maze Datasets
arXiv 2023
Structured World Representations in Maze-Solving Transformers
from 3 papers
Alex F. Spies
Can Rager
Cecilia Diniz Behn
Chris Mathwin
Guillaume Corlouer
Lucia Quirke
Michael Igorevich Ivanitskiy
Rusheb Shah
Samy Wu Fung
Tilman Räuker