keven980716 / weak-to-strong-deception
Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"
☆10Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for weak-to-strong-deception
- ☆19Updated last month
- ☆31Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆58Updated last month
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆26Updated 4 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆45Updated last month
- my commonly-used tools☆47Updated 3 months ago
- ☆44Updated 10 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆21Updated 4 months ago
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆15Updated 8 months ago
- ☆15Updated 3 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆45Updated 7 months ago
- [ATTRIB @ NeurIPS 2024] When Attention Sink Emerges in Language Models: An Empirical View☆27Updated 3 weeks ago
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆20Updated 5 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆12Updated last week
- AdaICL: Which Examples to Annotate of In-Context Learning? Towards Effective and Efficient Selection☆16Updated last year
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆22Updated 2 months ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆14Updated 6 months ago
- [NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$☆29Updated 2 weeks ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆27Updated last month
- Restore safety in fine-tuned language models through task arithmetic☆26Updated 7 months ago
- ☆33Updated last year
- Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning☆22Updated 3 months ago
- ☆24Updated last year
- ☆24Updated 5 months ago
- ☆15Updated last week
- Lightweight Adapting for Black-Box Large Language Models☆18Updated 8 months ago
- source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"☆18Updated last month
- Methods and evaluation for aligning language models temporally☆24Updated 8 months ago
- A Survey on the Honesty of Large Language Models☆44Updated last month
- ☆34Updated 3 months ago