ZHZisZZ / emulated-disalignmentLinks
[ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
☆38Updated last year
Alternatives and similar repositories for emulated-disalignment
Users that are interested in emulated-disalignment are comparing it to the libraries listed below
Sorting:
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆91Updated last year
- Rewarded soups official implementation☆60Updated 2 years ago
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆41Updated 8 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆77Updated 4 months ago
- ☆32Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆83Updated last year
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆66Updated 6 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆85Updated 6 months ago
- ☆43Updated 7 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- A Sober Look at Language Model Reasoning☆86Updated 2 weeks ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆188Updated 9 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆157Updated 6 months ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆148Updated 8 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆27Updated 11 months ago
- ☆46Updated last year
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆20Updated 6 months ago
- An index of algorithms for reinforcement learning from human feedback (rlhf))☆92Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆83Updated 7 months ago
- Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples☆44Updated 3 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆57Updated last year
- ☆51Updated last year
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆194Updated last year
- ☆31Updated 5 months ago
- Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts☆25Updated last year
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆57Updated last year
- ☆41Updated last year
- Code for "Towards Revealing the Mystery behind Chain of Thought: a Theoretical Perspective"☆20Updated 2 years ago