NUS-TRAIL / Unnatural_LanguageLinks
The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'
☆19Updated last month
Alternatives and similar repositories for Unnatural_Language
Users that are interested in Unnatural_Language are comparing it to the libraries listed below
Sorting:
- ☆15Updated 2 months ago
- Codebase for decoding compressed trust.☆24Updated last year
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated last month
- ☆35Updated 6 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆79Updated 8 months ago
- ☆41Updated 8 months ago
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆13Updated last year
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆27Updated 2 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 2 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆27Updated 4 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆18Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆37Updated last year
- ☆23Updated 3 months ago
- ☆20Updated last month
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆17Updated last year
- ☆20Updated 6 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 4 months ago
- ☆22Updated 3 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 5 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆39Updated last month
- ☆37Updated last year
- ☆30Updated last year
- Code for LLM_Catastrophic_Forgetting via SAM.☆10Updated last year
- SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433☆26Updated 6 months ago
- ☆21Updated 3 months ago
- ☆14Updated last week
- ☆26Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆88Updated 8 months ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆31Updated last year