TIDE: Token-Level Credit Assignment via Entropy-Gated Bounded Deviation
cs.LG, cs.AI
Submitted: 2026-05-05
Updated: 2026-11-12
Terminology
Sources
- RM-R1: Reward Modeling as Reasoning
- Training Verifiers to Solve Math Word Problems
- Pre-Trained Policy Discriminators are General Reward Models
- Group-in-Group Policy Optimization for LLM Agent Training
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off
- AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ESPO: Entropy Importance Sampling Policy Optimization
- Solving math word problems with process- and outcome-based feedback
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning
- Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
- Group Sequence Policy Optimization
- Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic
- Fine-Tuning Language Models from Human Preferences
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning