Don't Throw Away Data: Better Sequence Knowledge Distillation

Don't Throw Away Data: Better Sequence Knowledge Distillation

15 July 2024

Eleftheria Briakou

Rishabh Agarwal

Colin Cherry

Papers citing "Don't Throw Away Data: Better Sequence Knowledge Distillation"

4 / 4 papers shown

Title
Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation Verna Dankers Vikas Raunak VLM 56 0 0 03 Feb 2025
Better Instruction-Following Through Minimum Bayes Risk Ian Wu Patrick Fernandes Amanda Bertsch Seungone Kim Sina Pakazad Graham Neubig 48 9 0 03 Oct 2024
Faster Minimum Bayes Risk Decoding with Confidence-based Pruning Julius Cheng Andreas Vlachos 42 21 0 25 Nov 2023
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods M. Finkelstein Subhajit Naskar Mehdi Mirzazadeh Apurva Shah Markus Freitag 45 26 0 19 Sep 2023