Restore safety in fine-tuned language models through task arithmetic
☆33Mar 28, 2024Updated 2 years ago
Alternatives and similar repositories for resta
Users that are interested in resta are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This repository contains the implementation of the paper -- KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks☆15Sep 15, 2022Updated 4 years ago
- Code for the EMNLP 2022 Findings short paper "SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Train…☆12Feb 25, 2023Updated 3 years ago
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated 2 years ago
- ☆13Jun 19, 2025Updated last year
- This repository contains the dataset and the pytorch implementations of the models from the paper CIDER: Commonsense Inference for Dialog…☆28Oct 30, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for the COLING 2022 paper "DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification"☆19Oct 19, 2022Updated 4 years ago
- ☆13Jan 14, 2025Updated last year
- [NAACL 2024] Official Implementation of paper "Self-Adaptive Sampling for Efficient Video Question Answering on Image--Text Models"☆12May 14, 2026Updated 6 months ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆19Aug 22, 2024Updated 2 years ago
- ☆24Dec 8, 2024Updated last year
- ☆15Mar 14, 2024Updated 2 years ago
- [ICLR 2026] Official Implementation of the paper: "Two are better than one: Context window extension with multi-grained self-injection"☆12Feb 1, 2026Updated 9 months ago
- Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech und…☆43Mar 12, 2023Updated 3 years ago
- (ICLR '26) Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study☆13Oct 4, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆16Dec 2, 2025Updated 11 months ago
- [EMNLP 2022] This repository contains the official implementation of the paper "MM-Align: Learning Optimal Transport-based Alignment Dyna…☆33Mar 10, 2024Updated 2 years ago
- 🤖️ A collection of papers, blogs and projects of research agents.☆18Updated this week
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated last year
- Code for Spectral Insights into Data-Oblivious Critical Layers in Large Language Models.☆11Jun 17, 2025Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆108May 20, 2025Updated last year
- ☆13Oct 13, 2022Updated 4 years ago
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆17Jul 22, 2025Updated last year
- ☆48May 9, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code and data accompanying paper "Twitter Homophily: Network Based Prediction of User’s Occupation"☆19Jul 23, 2020Updated 6 years ago
- ☆13Jul 15, 2021Updated 5 years ago
- Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks☆56Jan 13, 2023Updated 3 years ago
- NLP deep learning model for multilingual toxicity detection in text 📚☆14Aug 10, 2020Updated 6 years ago
- Test LLMs against jailbreaks and unprecedented harms☆42Oct 19, 2024Updated 2 years ago
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling☆39Jul 12, 2024Updated 2 years ago
- This repository contains the source codes of the paper -- Exemplars-guided Empathetic Response Generation Controlled by the Elements of H…☆25Feb 1, 2023Updated 3 years 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…☆363Feb 23, 2024Updated 2 years ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆152Jul 19, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆10Mar 26, 2025Updated last year
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆17Jun 12, 2023Updated 3 years ago
- Create augmentation examples from MultiNLI by subject-object inversion and passivizing.☆17Feb 22, 2021Updated 5 years ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆552Mar 10, 2024Updated 2 years ago
- The official code repo for "Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets" in ICML 2025.☆59Feb 12, 2026Updated 9 months ago
- Domain Adaptation and Adapters☆16Feb 28, 2023Updated 3 years ago
- RoboQuest is a benchmark for goal-directed embodied exploration, in which a mobile manipulator must gather task-relevant information thro…☆11Oct 8, 2026Updated last month
Are these results useful?