Language Models can Evaluate Themselves via Probability Discrepancy

Language Models can Evaluate Themselves via Probability Discrepancy

17 May 2024

Bowen Yu

Chang Zhou

Papers citing "Language Models can Evaluate Themselves via Probability Discrepancy"

4 / 4 papers shown

Title
Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment Keming Lu Bowen Yu Chang Zhou Jingren Zhou 37 56 0 23 Jan 2024
WARM: On the Benefits of Weight Averaged Reward Models Alexandre Ramé Nino Vieillard Léonard Hussenot Robert Dadashi Geoffrey Cideron Olivier Bachem Johan Ferret 95 92 0 22 Jan 2024
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 301 11,730 0 04 Mar 2022
Teaching Machines to Read and Comprehend Karl Moritz Hermann Tomás Kociský Edward Grefenstette L. Espeholt W. Kay Mustafa Suleyman Phil Blunsom 170 3,504 0 10 Jun 2015