sail-sg / oat
๐พ OAT: Online AlignmenT for LLMs
โ24Updated last week
Related projects โ
Alternatives and complementary repositories for oat
- โ20Updated 4 months ago
- Rewarded soups official implementationโ50Updated last year
- โ35Updated 9 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversityโ38Updated 9 months ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)โ23Updated 10 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).โ14Updated last year
- Directional Preference Alignmentโ49Updated last month
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisionโ95Updated 2 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.โ24Updated 8 months ago
- GenRM-CoT: Data release for verification rationalesโ15Updated 3 weeks ago
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimizationโ52Updated 2 months ago
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!โ29Updated 3 months ago
- [ICML 2024] Self-Infilling Code Generationโ18Updated 6 months ago
- โ28Updated 11 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"โ46Updated last week
- This is the official repo for Towards Uncertainty-Aware Language Agent.โ22Updated 2 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"โ79Updated this week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.โ52Updated last week
- โ18Updated 2 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewardsโ39Updated 3 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Modelsโ29Updated 8 months ago
- โ41Updated last year
- โ15Updated last month
- โ24Updated last year
- โ27Updated 8 months ago
- This repository contains data, code and models for contextual noncompliance.โ18Updated 3 months ago
- Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Leโฆโ68Updated 7 months ago
- The code of โImproving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learningโโ15Updated 8 months ago
- โ85Updated 11 months ago