mjy1111 / BAKELinks
This is the repository for our paper: Untying the Reversal Curse via Bidirectional Language Model Editing
☆11Updated last week
Alternatives and similar repositories for BAKE
Users that are interested in BAKE are comparing it to the libraries listed below
Sorting:
- ☆25Updated 5 months ago
- ☆75Updated 5 months ago
- ☆18Updated 3 months ago
- ☆12Updated 8 months ago
- awesome SAE papers☆33Updated last week
- [AAAI 2024] History Matters: Temporal Knowledge Editing in Large Language Model☆13Updated last year
- ☆24Updated 2 years ago
- 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…☆84Updated 3 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆111Updated 8 months ago
- [ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing☆36Updated 9 months ago
- [ACL'2024 Findings] "Understanding and Patching Compositional Reasoning in LLMs"☆12Updated 9 months ago
- [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"☆123Updated 8 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆34Updated 6 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆39Updated 4 months ago
- ☆19Updated 4 months ago
- ☆44Updated 6 months ago
- ☆74Updated last year
- EMNLP'2023: Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration☆35Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆110Updated last year
- ☆13Updated last year
- Source code of our paper MIND, ACL 2024 Long Paper☆41Updated last year
- ☆11Updated 3 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆28Updated 2 months ago
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improving☆19Updated 7 months ago
- ☆25Updated 7 months ago
- ☆17Updated last year
- ☆33Updated last year
- Model merging is a highly efficient approach for long-to-short reasoning.☆56Updated this week
- ☆38Updated 2 months ago