DYR1 / MoGULinks
Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.
☆15Updated 7 months ago
Alternatives and similar repositories for MoGU
Users that are interested in MoGU are comparing it to the libraries listed below
Sorting:
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆97Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆85Updated 4 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆36Updated 2 weeks ago
- [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…☆26Updated 11 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- ☆41Updated 11 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆80Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆81Updated last year
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆69Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 7 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆158Updated 5 months ago
- ☆39Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆82Updated 11 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆87Updated 3 months ago
- Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"☆31Updated 2 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆155Updated last year
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆59Updated 8 months ago
- ☆182Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆142Updated last year
- [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".☆128Updated 10 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆104Updated last year
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 3 months ago
- LLM Unlearning☆174Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆30Updated last year
- [NeurIPS'24] Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models☆62Updated 8 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- This repository presents the original implementation of Pretraining Data Detection for Large Language Models: A Divergence-based Calibrat…☆17Updated 3 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆116Updated last year