WanliYoung / Collapse-in-Model-Editing
Code and data repository for two papers (ACL & EMNLP 2024) on the topic of collapse in model editing.
☆10Updated 4 months ago
Alternatives and similar repositories for Collapse-in-Model-Editing:
Users that are interested in Collapse-in-Model-Editing are comparing it to the libraries listed below
- ☆12Updated 7 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆109Updated 7 months ago
- Evaluating the Ripple Effects of Knowledge Editing in Language Models☆55Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆67Updated 2 years ago
- ☆24Updated 2 years ago
- ☆38Updated last year
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆63Updated last year
- ☆17Updated last year
- ☆34Updated last month
- This is the repo for the survey of Bias and Fairness in IR with LLMs.☆52Updated 3 weeks ago
- ☆26Updated last year
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 6 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆31Updated 5 months ago
- [ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing☆35Updated 8 months ago
- ☆41Updated last year
- ☆21Updated 4 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- ☆57Updated 9 months ago
- ☆73Updated 11 months ago
- ☆23Updated last year
- ☆32Updated 11 months ago
- ☆22Updated 6 months ago
- ☆21Updated last month
- self-adaptive in-context learning☆43Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆98Updated this week
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 5 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1☆13Updated last year
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆75Updated 2 months ago
- ☆17Updated last year