TokenBuncher constrains response entropy via entropy-as-reward RL and a Token Noiser to stop harmful RL fine-tuning while keeping benign performance intact.
Training language models to follow instructions with human feedback
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator.
citing papers explorer
-
Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
TokenBuncher constrains response entropy via entropy-as-reward RL and a Token Noiser to stop harmful RL fine-tuning while keeping benign performance intact.
-
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator.