lasgroup / SafetyPolytopeLinks
Learning Safety Constraints for Large Language Models (ICML2025)
☆25Updated 3 months ago
Alternatives and similar repositories for SafetyPolytope
Users that are interested in SafetyPolytope are comparing it to the libraries listed below
Sorting:
- Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"☆32Updated last year
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆37Updated last year
- Rewarded soups official implementation☆62Updated 2 years ago
- ☆34Updated 2 years ago
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆42Updated last year
- ☆19Updated last year
- Attack AlphaZero Go agents (NeurIPS 2022)☆22Updated 2 years ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated last year
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆38Updated last year
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆37Updated last year
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆44Updated 9 months ago
- [NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning☆34Updated 4 years ago
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆62Updated last year
- Official repository for Beyond Binary Rewards: Training LMs to Reason about Their Uncertainty☆44Updated 3 months ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆19Updated last year
- Codebase for "Uni[MASK]: Unified Inference in Sequential Decision Problems"☆57Updated last year
- Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (M…☆29Updated last year
- Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.☆10Updated last year
- [NeurIPS 2020 Spotlight] State-adversarial PPO for robust deep reinforcement learning☆31Updated 4 years ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆69Updated 7 months ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆26Updated last month
- ☆19Updated last year
- ☆11Updated 11 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆29Updated last year
- Code for "Task-Agnostic Continual RL: In Praise of a Simple Baseline"☆34Updated 2 years ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆78Updated 5 months ago
- [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective☆40Updated 2 months ago
- The official code release for Q#: Provably Optimal Distributional RL for LLM Post-Training☆17Updated 8 months ago
- Offline RLHF codebase implementation for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human …☆41Updated last year
- A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.☆45Updated 10 months ago