[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
☆191Jan 16, 2025Updated last year
Alternatives and similar repositories for aligner
Users that are interested in aligner are comparing it to the libraries listed below
Sorting:
- Self-Supervised Alignment with Mutual Information☆20May 24, 2024Updated last year
- Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts☆16Feb 26, 2024Updated 2 years ago
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Feb 22, 2024Updated 2 years ago
- The reproduct of the paper - Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction☆22May 29, 2024Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,591Nov 24, 2025Updated 3 months ago
- SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enh…☆34Aug 20, 2024Updated last year
- ☆13Jan 22, 2025Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆91May 2, 2025Updated 10 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆345Feb 23, 2024Updated 2 years ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75May 20, 2025Updated 10 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆90Mar 15, 2024Updated 2 years ago
- ☆21Jun 22, 2025Updated 8 months ago
- Improving Math reasoning through Direct Preference Optimization with Verifiable Pairs☆19Mar 20, 2025Updated last year
- ☆197Nov 26, 2023Updated 2 years ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Mar 8, 2024Updated 2 years ago
- ☆41Jul 6, 2025Updated 8 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆48Jan 19, 2024Updated 2 years ago
- AI Alignment: A Comprehensive Survey☆136Nov 2, 2023Updated 2 years ago
- Codebase for Inference-Time Policy Adapters☆25Nov 3, 2023Updated 2 years ago
- ☆314Jun 9, 2024Updated last year
- ☆21Jul 26, 2025Updated 7 months ago
- ☆33Jun 24, 2024Updated last year
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆15Apr 20, 2024Updated last year
- ☆16Jul 23, 2024Updated last year
- Official repository for ORPO☆473May 31, 2024Updated last year
- NeurIPS2022: Constrained Update Projection Approach to Safe Policy Optimization☆13Apr 10, 2023Updated 2 years ago
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆29Apr 2, 2025Updated 11 months ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,961Aug 9, 2025Updated 7 months ago
- Recipes to train reward model for RLHF.☆1,521Apr 24, 2025Updated 10 months ago
- ☆24Oct 14, 2024Updated last year
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆176Oct 27, 2023Updated 2 years ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year
- Implementation of "Decoding-time Realignment of Language Models", ICML 2024.☆21Jun 17, 2024Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆87Oct 26, 2025Updated 4 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆107May 20, 2025Updated 10 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆47Apr 15, 2025Updated 11 months ago
- Lightweight Adapting for Black-Box Large Language Models☆25Feb 15, 2024Updated 2 years ago
- Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.☆12Feb 11, 2024Updated 2 years ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆87Mar 23, 2025Updated 11 months ago