yfqiu-nlp / sea-llm
Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"
☆15Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for sea-llm
- ☆12Updated last month
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆51Updated this week
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆62Updated 2 years ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆14Updated 6 months ago
- ☆44Updated 2 months ago
- ☆26Updated 6 months ago
- Restore safety in fine-tuned language models through task arithmetic☆26Updated 7 months ago
- Methods and evaluation for aligning language models temporally☆24Updated 8 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆21Updated 4 months ago
- ☆15Updated 3 months ago
- ☆40Updated 11 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆51Updated last month
- ☆33Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆17Updated last month
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆15Updated 8 months ago
- ☆34Updated 3 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆45Updated 7 months ago
- ☆15Updated last week
- ☆79Updated last year
- ☆34Updated 3 months ago
- [ATTRIB @ NeurIPS 2024] When Attention Sink Emerges in Language Models: An Empirical View☆27Updated 3 weeks ago
- ☆49Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆116Updated 3 weeks ago
- ☆27Updated last year
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆32Updated 3 weeks ago
- ☆24Updated last year
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆58Updated 11 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆46Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆69Updated 8 months ago