A framework for mitigating malicious RLHF feedback in LLM training using consensus based reward
Z
Zafaryab Haider
M
Md Hafizur Rahman
V
Vijay Devabhaktuni
S
Shane Moeykens
P
Prabuddha Chakraborty
Article Details
Journal
Scientific Reports
Volume / Issue
Vol. 15, Issue 1
Published
March 17, 2025
ISSN
2045-2322
Publisher
Nature Portfolio
Authors (5)
Z
Zafaryab Haider
M
Md Hafizur Rahman
V
Vijay Devabhaktuni
S
Shane Moeykens
P
Prabuddha Chakraborty
Related Articles from this Journal
AI models of unstable flow exhibit hallucination
Ramdhan Wibawa, Birendra Jha
Aug 2026
10.1038/s41598-026-64023-8
The MCAA-YOLO + XPBI integrated model provides a hybrid intelligent measurement method for predicting the body weight of Hu sheep
Hang Zhang, Yuang Cheng et al.
Aug 2026
10.1038/s41598-026-64075-w
Application of iron nano-biofertilizers as a sustainable approach to enhance growth and micronutrient uptake in soybean
Ava Mohrazi, Reza Ghasemi-Fasaei
Aug 2026
10.1038/s41598-026-66011-4
Adolescents’ status-dependent public and private conformity to prosocial and antisocial decisions in a public goods game
Niloofar Saeedi, Khatereh Borhani et al.
Aug 2026
10.1038/s41598-026-64831-y
An explainable hierarchical capsule network framework for supporting expert sensory evaluation of herbal medicines with natural language generation
Hyein Lee, Dae-Hyun Jung
Aug 2026
10.1038/s41598-026-64156-w