RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
HelpSteer3-preference: Open human-annotated preference data across diverse tasks and languages
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2025 4verdicts
UNVERDICTED 4representative citing papers
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
Introduces a latent user quality model and EM algorithm to infer and filter noisy user-provided pairwise preferences for improved LLM alignment.
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.
citing papers explorer
-
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
-
Users as Annotators: LLM Preference Learning from Comparison Mode
Introduces a latent user quality model and EM algorithm to infer and filter noisy user-provided pairwise preferences for improved LLM alignment.
-
Reinforcement Learning from Human Feedback
The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.