princeton-pli / what-makes-good-rmLinks
What Makes a Reward Model a Good Teacher? An Optimization Perspective
☆36Updated 2 months ago
Alternatives and similar repositories for what-makes-good-rm
Users that are interested in what-makes-good-rm are comparing it to the libraries listed below
Sorting:
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆66Updated 4 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆116Updated 4 months ago
- A Sober Look at Language Model Reasoning☆81Updated 2 months ago
- ☆24Updated 3 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆85Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆44Updated last month
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆38Updated 6 months ago
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆13Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆118Updated last month
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆36Updated 3 months ago
- Rewarded soups official implementation☆60Updated last year
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆30Updated 7 months ago
- Lightweight Adapting for Black-Box Large Language Models☆23Updated last year
- ☆34Updated 7 months ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆20Updated 4 months ago
- A repo for open research on building large reasoning models☆92Updated this week
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆28Updated last year
- ☆15Updated last year
- ☆161Updated 3 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆66Updated 5 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆36Updated last month
- Discriminative Constrained Optimization for Reinforcing Large Reasoning Models☆36Updated last week
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆123Updated 11 months ago
- Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning☆34Updated 9 months ago
- ☆40Updated 4 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆72Updated 2 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 4 months ago
- Test-time-training on nearest neighbors for large language models☆45Updated last year
- ☆44Updated last year