This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
☆29Mar 11, 2025Updated 11 months ago
Alternatives and similar repositories for Safety-Tax
Users that are interested in Safety-Tax are comparing it to the libraries listed below
Sorting:
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆28Apr 2, 2025Updated 10 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆25Sep 10, 2024Updated last year
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated 8 months ago
- This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"☆54Feb 2, 2025Updated last year
- ☆16Feb 8, 2024Updated 2 years ago
- ☆18Nov 10, 2024Updated last year
- Exploring Model Kinship for Merging Large Language Models☆27Apr 16, 2025Updated 10 months ago
- ☆24Feb 17, 2026Updated last week
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆49Jan 15, 2026Updated last month
- A survey on harmful fine-tuning attack for large language model☆232Updated this week
- [ICLR24] AutoVP: An Automated Visual Prompting Framework and Benchmark☆21Sep 18, 2025Updated 5 months ago
- Official implementation of "OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging".☆43Oct 30, 2025Updated 4 months ago
- [NeurIPS 2024] AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models☆33Jun 9, 2025Updated 8 months ago
- ☆24Dec 8, 2024Updated last year
- Pytorch implementation of gnn meta attack (mettack). Paper title: Adversarial Attacks on Graph Neural Networks via Meta Learning.☆21Mar 23, 2021Updated 4 years ago
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- [CVPR23] "Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations" by Lei Hsi…☆24Sep 17, 2025Updated 5 months ago
- Restore safety in fine-tuned language models through task arithmetic☆32Mar 28, 2024Updated last year
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆33Apr 7, 2025Updated 10 months ago
- ☆38Jan 15, 2025Updated last year
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆36Apr 7, 2025Updated 10 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Mar 30, 2025Updated 11 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆174Apr 23, 2025Updated 10 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆97Feb 21, 2025Updated last year
- Official implementation of MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems☆75Jun 26, 2025Updated 8 months ago
- Debiasing Through Data Attribution☆12May 23, 2024Updated last year
- something for paper agent☆11Dec 18, 2024Updated last year
- Jupyter notebooks for the neuroptica simulator☆11Mar 7, 2019Updated 6 years ago
- ☆11Aug 20, 2025Updated 6 months ago
- Code for the paper "A Boolean Task Algebra For Reinforcement Learning"☆11Dec 8, 2022Updated 3 years ago
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated last year
- ☆44Oct 1, 2024Updated last year
- [AAAI 2024] DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models☆12Dec 5, 2024Updated last year
- ☆11Aug 31, 2025Updated 6 months ago
- ☆19May 14, 2025Updated 9 months ago
- ☆14Feb 26, 2025Updated last year
- [ICML 2022 Spotlight] Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks☆11May 21, 2023Updated 2 years ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated last month