keven980716 / weak-to-strong-deceptionLinks
[ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"
☆13Updated last year
Alternatives and similar repositories for weak-to-strong-deception
Users that are interested in weak-to-strong-deception are comparing it to the libraries listed below
Sorting:
- ☆30Updated last year
- Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning☆34Updated 9 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆37Updated last month
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆46Updated 10 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆26Updated last year
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆66Updated 5 months ago
- ☆13Updated last month
- A Sober Look at Language Model Reasoning☆81Updated 2 months ago
- [NeurIPS 2024] Code and Data Repo for Paper "Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning"☆27Updated last year
- [AAAI 2024] MELO: Enhancing Model Editing with Neuron-indexed Dynamic LoRA☆26Updated last year
- SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433☆28Updated 8 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆88Updated 10 months ago
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆58Updated 8 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 3 months ago
- ☆15Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆59Updated 11 months ago
- Source code for the TMLR paper "Black-Box Prompt Learning for Pre-trained Language Models"☆56Updated last year
- Official implementation for "ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation"☆19Updated 3 weeks ago
- code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning☆17Updated last year
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆61Updated last year
- ☆24Updated 3 months ago
- ☆36Updated last year
- What Makes a Reward Model a Good Teacher? An Optimization Perspective☆36Updated 2 months ago
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆28Updated last year