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.
Offline rl for natural language generation with implicit language q learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
DiPS uses Implicit Q-Learning over dialogue history embeddings to select persuasion policies turn-by-turn, raising evacuation success above zero-shot LLM and RAG baselines in simulation and human studies.
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
Offline RL post-training boosts code generation performance in LLMs, with larger gains for small models and hard problems, using pre-collected 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.
-
Conditional Attribute Estimation with Autoregressive Sequence Models
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
DiPS uses Implicit Q-Learning over dialogue history embeddings to select persuasion policies turn-by-turn, raising evacuation success above zero-shot LLM and RAG baselines in simulation and human studies.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
-
Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
Offline RL post-training boosts code generation performance in LLMs, with larger gains for small models and hard problems, using pre-collected datasets.