Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24]
☆26Jun 14, 2024Updated last year
Alternatives and similar repositories for ULD
Users that are interested in ULD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] FLAT: LLM Unlearning via Loss Adjustment with Only Forget Data☆14Feb 26, 2025Updated last year
- ☆28Feb 25, 2025Updated last year
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆30Oct 1, 2024Updated last year
- [NeurIPS D&B '25] The one-stop repository for LLM unlearning☆533Mar 18, 2026Updated last month
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Implementation of paper 'Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing'☆24Jun 9, 2024Updated last year
- 🚀 Sliding Window Attention Training for Efficient Large Language Models☆16Dec 8, 2025Updated 4 months ago
- Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding.☆13Nov 19, 2024Updated last year
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆18Sep 16, 2025Updated 7 months ago
- ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models☆44Nov 18, 2025Updated 5 months ago
- ☆60May 1, 2022Updated 4 years ago
- ☆14May 7, 2024Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆94Sep 30, 2024Updated last year
- ☆16Sep 5, 2023Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆17Nov 20, 2024Updated last year
- ☆16Oct 16, 2023Updated 2 years ago
- [NeurIPS 2024] Large Language Model Unlearning via Embedding-Corrupted Prompts☆40Sep 26, 2024Updated last year
- ☆45Apr 7, 2026Updated 3 weeks ago
- [ACL 2024 Findings] Learning Fine-Grained Grounded Citations for Attributed Large Language Models☆19Oct 24, 2024Updated last year
- Official resource for paper Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (ACL 20…☆15Aug 12, 2024Updated last year
- Official code implement of "Your Diffusion Model is Secretly a Certifiably Robust Classifier"☆18Feb 2, 2024Updated 2 years ago
- ☆37Nov 14, 2025Updated 5 months ago
- WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights (CVPR 2024) - Official Pytorch Code☆19Mar 31, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"☆44Oct 3, 2025Updated 7 months ago
- [ICML 2025] Official PyTorch implementation of "NegMerge: Sign-Consensual Weight Merging for Machine Unlearning"☆14Nov 25, 2025Updated 5 months ago
- ☆12Jan 27, 2017Updated 9 years ago
- For prospective and new joiners☆10Oct 25, 2024Updated last year
- Implementation for "Correcting Diffusion Generation through Resampling" [CVPR 2024]☆34Dec 12, 2023Updated 2 years ago
- ☆19Mar 26, 2022Updated 4 years ago
- Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends [NeurIPS 2023]☆10Jan 28, 2024Updated 2 years ago
- Codebase for Instruction Following without Instruction Tuning☆36Sep 24, 2024Updated last year
- ☆23Sep 20, 2023Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A benchmark for evaluating the efficiency of LLM-generated code☆17Apr 17, 2025Updated last year
- ☆16May 16, 2025Updated 11 months ago
- Watermarking LLM papers up-to-date☆12Dec 17, 2023Updated 2 years ago
- We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.☆28Dec 16, 2024Updated last year
- ☆20Dec 29, 2024Updated last year
- ☆19Aug 4, 2025Updated 9 months ago
- 主题：计算认知科学(Computational Cognitive Science)。此仓库诞生背景为IA003结业BP，仍处于萌芽期，内容设置有待转正。下一次大规模更新估计在三四年之后。☆17May 22, 2019Updated 6 years ago