Forecasting How RLHF Responds to Reward-Model Edits Before Training
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-17
Terminology
Sources
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- Distilling the Knowledge in a Neural Network
- Categorizing Variants of Goodhart's Law
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
- Reward Hacking as Equilibrium under Finite Evaluation
- Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent
- Reward Model Overoptimisation in Iterated RLHF
- Qwen3 Technical Report
- Fine-Tuning Language Models from Human Preferences
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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