scalable-model-editing / unified-model-editingLinks
We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
☆24Updated 7 months ago
Alternatives and similar repositories for unified-model-editing
Users that are interested in unified-model-editing are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- ☆89Updated last year
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆59Updated last week
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- This is a repository for "PMET: Precise Model Editing in a Transformer"☆53Updated last year
- Exploration of automated dataset selection approaches at large scales.☆47Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 3 months ago
- [ACL 2025] Knowledge Unlearning for Large Language Models☆39Updated 3 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆91Updated 8 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆29Updated this week
- Code to enable layer-level steering in LLMs using sparse auto encoders☆22Updated 3 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- Code repo for the model organisms and convergent directions of EM papers.☆21Updated 2 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆12Updated 4 months ago
- ☆51Updated 3 months ago
- ☆121Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- ☆27Updated last year
- ☆89Updated last year
- ☆29Updated 5 months ago
- Codebase for Math Neurosurgery: Isolating LLMs' Math Reasoning Abilities Using Only Forward Passes☆19Updated last month
- [NeurIPS'24 Spotlight] Observational Scaling Laws☆56Updated 10 months ago
- ☆27Updated 5 months ago