GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
Learning to summarize with human feedback
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
citing papers explorer
-
Group-in-Group Policy Optimization for LLM Agent Training
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
-
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.
-
Jailbroken: How Does LLM Safety Training Fail?
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.