REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback
Paper
•
2505.06548
•
Published
•
30
AI & ML interests
A group working towards furthering research in the field of Sanskrit Computational Linguistics
Recent Activity
View all activity
Pretam
authored
a
paper
about 2 months ago
barca-boy
updated
a
model
4 months ago
barca-boy
published
a
model
4 months ago
barca-boy
updated
a
model
5 months ago
[bot] Conversion to Parquet
1
#1 opened 8 months ago
by
parquet-converter
pu239
updated
a
dataset
8 months ago
pu239
authored
a
paper
10 months ago