This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
☆29Mar 11, 2025Updated last year
Alternatives and similar repositories for Safety-Tax
Users that are interested in Safety-Tax are comparing it to the libraries listed below
Sorting:
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆35Mar 22, 2025Updated 11 months ago
- ☆18Nov 10, 2024Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated 9 months ago
- [NeurIPS'24] "NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes"☆10Sep 18, 2025Updated 6 months ago
- [ACL 2023 findings] Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization☆17Aug 26, 2023Updated 2 years ago
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆33Apr 7, 2025Updated 11 months ago
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated last year
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆49Jan 15, 2026Updated 2 months ago
- [NeurIPS 2024] AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models☆33Jun 9, 2025Updated 9 months ago
- A survey on harmful fine-tuning attack for large language model☆235Feb 25, 2026Updated 3 weeks ago
- [ICLR24] AutoVP: An Automated Visual Prompting Framework and Benchmark☆22Sep 18, 2025Updated 6 months ago
- Let you in a meta world of The Palace Museum☆20Aug 30, 2025Updated 6 months ago
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 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
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 Spotlight)☆15Mar 31, 2025Updated 11 months ago
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆36Apr 7, 2025Updated 11 months ago
- Restore safety in fine-tuned language models through task arithmetic☆32Mar 28, 2024Updated last year
- ☆13Jul 2, 2025Updated 8 months ago
- [CVPR23] "Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations" by Lei Hsi…☆24Sep 17, 2025Updated 6 months ago
- [ACL 2025] Official implementation of the "CoT-ICL Lab" framework☆11Oct 10, 2025Updated 5 months ago
- Debiasing Through Data Attribution☆12May 23, 2024Updated last year
- ☆50Oct 24, 2023Updated 2 years ago
- https://arxiv.org/abs/2404.10917☆14Mar 18, 2025Updated last year
- The official repository for AdaMuon☆35Aug 27, 2025Updated 6 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆176Apr 23, 2025Updated 10 months ago
- [CVPR 2025] LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs☆13Jun 20, 2025Updated 9 months ago
- ☆18Apr 7, 2025Updated 11 months ago
- ☆44Oct 1, 2024Updated last year
- ISO 15919 transliteration for Devanagari text☆11Dec 27, 2014Updated 11 years ago
- ☆14Apr 16, 2025Updated 11 months ago
- ☆21Nov 16, 2018Updated 7 years ago
- ☆16Jun 14, 2023Updated 2 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Mar 30, 2025Updated 11 months ago
- ☆14Jan 30, 2021Updated 5 years ago
- ☆14Feb 26, 2025Updated last year
- Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)☆12Apr 29, 2024Updated last year
- ☆39Jan 15, 2025Updated last year
- Code for Representation Bending Paper☆16Jul 15, 2025Updated 8 months ago
- Code Repository for "A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models".☆15Oct 14, 2022Updated 3 years ago