Article
Argunauts Training Phase III: RLVF with Hindsight Instruction Relabeling, Self-Correction and Dynamic Curriculum
By
•
•
1Hyun Ryu
hyun1905
·
AI & ML interests
None yet
Recent Activity
liked
a dataset
7 days ago
DebateLabKIT/arguments-and-debates
authored
a paper
2 months ago
Reasoning Model is Stubborn: Diagnosing Instruction Overriding in
Reasoning Models
Organizations
None yet
upvoted
an
article
5 days ago
liked
a
dataset
7 days ago
authored
a
paper
2 months ago
upvoted
a
paper
2 months ago
upvoted
4
articles
5 months ago
Article
syncIAL🍏: A Multi-Purpose Synthetic Debate and Argument Mapping Corpus
By
•
•
4
Article
Argunauts Training Phase II: Selfplay Finetuning Line-By-Line
By
•
•
5
Article
Argunauts Training Phase I: Continual Pretraining on Synthetic Data
By
•
•
2
Article
Argunauts: Open LLMs that Master Argument Analysis with Argdown
By
•
•
7