BLADE uses Bayesian list-wise alignment with dynamic estimation to create a self-evolving target that overcomes limitations of static references in LLM-based recommendation, yielding sustained gains in ranking and complex metrics.
Variational best-of-n alignment
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
FADE is a self-adapting advantage for policy-gradient RL that reads training dynamics to balance positive/negative gradient mass and difficulty focus, yielding faster peak performance and better accuracy-diversity trade-offs than static baselines on LLM reasoning benchmarks.
citing papers explorer
-
Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation
BLADE uses Bayesian list-wise alignment with dynamic estimation to create a self-evolving target that overcomes limitations of static references in LLM-based recommendation, yielding sustained gains in ranking and complex metrics.
-
Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL
FADE is a self-adapting advantage for policy-gradient RL that reads training dynamics to balance positive/negative gradient mass and difficulty focus, yielding faster peak performance and better accuracy-diversity trade-offs than static baselines on LLM reasoning benchmarks.