R³L combines reflect-then-retry exploration, pivotal credit assignment, and positive amplification in RL for LLMs, reporting 5-52% relative gains on agentic and reasoning tasks with stable training.
arXiv preprint arXiv:2204.14146 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A three-stage fine-tuning process uses human ratings to train a reward model and then improves text-to-image alignment by maximizing reward-weighted likelihood.
Self-Refine boosts LLM outputs by ~20% on average across seven tasks by having the same model iteratively generate, critique, and refine its own responses.
citing papers explorer
-
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
R³L combines reflect-then-retry exploration, pivotal credit assignment, and positive amplification in RL for LLMs, reporting 5-52% relative gains on agentic and reasoning tasks with stable training.
-
Aligning Text-to-Image Models using Human Feedback
A three-stage fine-tuning process uses human ratings to train a reward model and then improves text-to-image alignment by maximizing reward-weighted likelihood.
-
Self-Refine: Iterative Refinement with Self-Feedback
Self-Refine boosts LLM outputs by ~20% on average across seven tasks by having the same model iteratively generate, critique, and refine its own responses.
- Human agency in initial human-AI proof formalization workflows