ykwon0407 / DataInf
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
☆63Updated 5 months ago
Alternatives and similar repositories for DataInf:
Users that are interested in DataInf are comparing it to the libraries listed below
- AI Logging for Interpretability and Explainability🔬☆110Updated 9 months ago
- ☆17Updated 3 weeks ago
- ☆21Updated 2 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated 3 weeks ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆73Updated last month
- ☆66Updated 3 years ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆18Updated 8 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆74Updated 3 months ago
- ☆53Updated 8 months ago
- Code for Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities (NeurIPS'24)☆17Updated 3 months ago
- A resource repository for representation engineering in large language models☆116Updated 4 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆42Updated 5 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated last month
- ☆42Updated last month
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆41Updated 4 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 4 months ago
- ☆47Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆98Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆83Updated 8 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- ☆34Updated 6 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆37Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆134Updated 10 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆34Updated 2 months ago
- ☆37Updated last year
- ☆93Updated last year
- General-purpose activation steering library☆54Updated 2 months ago
- ☆38Updated last year
- ☆29Updated 11 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 2 months ago