UniR is a composable reasoning module trained with verifiable rewards and added to frozen LLMs via logit summation, enabling modular composition and weak-to-strong generalization across tasks and model sizes.
Genarm: Reward guided generation with autoregressive reward model for test-time alignment
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
Reward-weighted classifier-free guidance approximates Q-function policy improvement in autoregressive models, enabling test-time reward optimization and faster RL convergence via distillation.
REFORM uses reward-guided controlled decoding to generate adversarial failures and augments training data to improve reward model robustness on preference datasets.
citing papers explorer
-
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
UniR is a composable reasoning module trained with verifiable rewards and added to frozen LLMs via logit summation, enabling modular composition and weak-to-strong generalization across tasks and model sizes.
-
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
-
Common-agency Games for Multi-Objective Test-Time Alignment
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
-
Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
Reward-weighted classifier-free guidance approximates Q-function policy improvement in autoregressive models, enabling test-time reward optimization and faster RL convergence via distillation.
-
Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
REFORM uses reward-guided controlled decoding to generate adversarial failures and augments training data to improve reward model robustness on preference datasets.