Science Publishing Group
Predatory publisher
📊 Rating
3 news mentions · 👍 0 likes · 👎 0 dislikes
📌 Topics
- Artificial Intelligence (3)
- Machine Learning (3)
- AI Safety (2)
- Data Privacy (1)
🏷️ Keywords
Machine Learning Research (3) · RLHF (1) · Reward Hacking (1) · Bayesian Modeling (1) · LLM Alignment (1) · BNRM (1) · AI Accuracy (1) · FedPS (1) · Federated Learning (1) · Data Preprocessing (1) · Privacy-Preserving AI (1) · arXiv (1) · Decentralized Computing (1) · LLM (1) · Data Attribution (1) · Post-Training (1) · Emergent Behavior (1) · Activation Vectors (1)
📖 Key Information
📰 Related News (3)
-
🇺🇸 Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
arXiv:2602.10623v1 Announce Type: cross Abstract: Reward models learned from human preferences are central to aligning large language models (LLMs) v...
-
🇺🇸 FedPS: Federated data Preprocessing via aggregated Statistics
arXiv:2602.10870v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple parties to collaboratively train machine learning models w...
-
🇺🇸 In-the-Wild Model Organisms: Mitigating Undesirable Emergent Behaviors in Production LLM Post-Training via Data Attribution
arXiv:2602.11079v1 Announce Type: cross Abstract: We propose activation-based data attribution, a method that traces behavioral changes in post-train...
🔗 Entity Intersection Graph
People and organizations frequently mentioned alongside Science Publishing Group:
- 🌐 Data preprocessing (1 shared articles)
- 🌐 Large language model (1 shared articles)
- 🌐 Reinforcement learning from human feedback (1 shared articles)