Thartvigsen / GRACE
[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
☆73Updated 2 months ago
Alternatives and similar repositories for GRACE:
Users that are interested in GRACE are comparing it to the libraries listed below
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆66Updated 2 years ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆107Updated 11 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆106Updated 6 months ago
- ☆92Updated last year
- ☆50Updated last year
- General-purpose activation steering library☆50Updated 2 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 4 months ago
- ☆37Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆50Updated 3 months ago
- A Survey of Hallucination in Large Foundation Models☆54Updated last year
- ☆30Updated 10 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆144Updated 5 months ago
- ☆30Updated 5 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆90Updated 2 weeks ago
- ☆47Updated last year
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆53Updated 11 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆34Updated 2 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆69Updated last week
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 8 months ago
- Restore safety in fine-tuned language models through task arithmetic☆27Updated 11 months ago
- Evaluating the Ripple Effects of Knowledge Editing in Language Models☆54Updated 11 months ago
- ☆37Updated last year
- ☆47Updated 7 months ago
- This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)☆100Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆107Updated 9 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆58Updated 2 years ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 8 months ago
- ☆72Updated 9 months ago
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆70Updated last year
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆29Updated 9 months ago