Article
Argunauts Update: Learning Formal Argument Analysis with RLVF and HIRPO
•
1
Gregor Betz PRO
ggbetz
AI & ML interests
Reasoning, AGI, AI Safety, AI Reliability
Recent Activity
upvoted an article 10 days ago
TRL v1.0: Post-Training Library Built to Move with the Field updated a Space about 1 month ago
ggbetz/trackio published a Space about 1 month ago
ggbetz/trackioOrganizations
published an article 4 months ago
published an article 9 months ago
Article
Argunauts Training Phase III: RLVF with Hindsight Instruction Relabeling, Self-Correction and Dynamic Curriculum
•
2
published an article about 1 year ago
Article
Argunauts Training Phase II: Selfplay Finetuning Line-By-Line
•
5
published an article about 1 year ago
Article
Argunauts Training Phase I: Continual Pretraining on Synthetic Data
•
2
published an article about 1 year ago
Article
Argunauts: Open LLMs that Master Argument Analysis with Argdown
•
11
published an article about 1 year ago
Article
syncIAL🍏: A Multi-Purpose Synthetic Debate and Argument Mapping Corpus
•
4
published an article almost 2 years ago
Article
Introducing the Open Chain of Thought Leaderboard
- +2
•
37
published an article almost 2 years ago
Article
Introducing the Open Chain of Thought Leaderboard
- +2
•
37