The cancellation hypothesis shows how rollout-level rewards produce token-level credit assignment in critic-free RL through cancellation of opposing signals on shared tokens, with empirical support and batching interventions that enhance performance.
Unintentional unalignment: Likelihood displacement in direct preference optimization.arXiv preprint arXiv:2410.08847
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits
The cancellation hypothesis shows how rollout-level rewards produce token-level credit assignment in critic-free RL through cancellation of opposing signals on shared tokens, with empirical support and batching interventions that enhance performance.