ZHZisZZ / emulated-disalignmentLinks
[ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
☆36Updated 10 months ago
Alternatives and similar repositories for emulated-disalignment
Users that are interested in emulated-disalignment are comparing it to the libraries listed below
Sorting:
- Rewarded soups official implementation☆58Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆79Updated 9 months ago
- ☆30Updated 11 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆23Updated 7 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆69Updated 5 months ago
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆34Updated 3 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆79Updated 2 months ago
- ☆40Updated last year
- ☆38Updated 2 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆27Updated 2 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- ☆41Updated 8 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆75Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆58Updated 2 months ago
- A Sober Look at Language Model Reasoning☆52Updated last week
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆125Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆140Updated 3 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆21Updated 8 months ago
- Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples☆35Updated last month
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆57Updated 8 months ago
- ☆58Updated 10 months ago
- ☆49Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆28Updated 6 months ago
- Directional Preference Alignment☆56Updated 8 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆35Updated 3 weeks ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 4 months ago
- Official repository for 'Safety Challenges in Large Reasoning Models: A Survey' - Exploring safety risks, attacks, and defenses for Large…☆36Updated last week
- A Survey on the Honesty of Large Language Models☆57Updated 5 months ago