EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
- 2.9k
- Jupyter Notebook
- MIT
- 12 d ago
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Must-read Papers on Knowledge Editing for Large Language Models.
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
A resource repository for machine unlearning in large language models
Neural networks and weight-space programming in Rust, JavaScript and WebAssembly. Inspect activations, edit weights, evaluate candidates, train small models, and explicitly promote or roll back revisions.
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
Decomposing and Editing Predictions by Modeling Model Computation
[ACL 2025] How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
[EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
[ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
[ACL 2024] An Easy-to-use Hallucination Detection Framework for LLMs.
[ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models
[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing
Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.
Image text to text model, used with gguf.
A curated collection of Weight-Space Programming and weight-centric research, covering weight understanding, generation, editing, merging, transfer, and continual learning.
An editable, auditable 807K-param byte-level LLM: CRUD single facts with provable per-edit locality, and abstain when unsure instead of guessing. CPU, offline.
Image text to text model, used with transformers.
Image text to text model, used with gguf.
Image text to text model, used with transformers.
Open-source weight space editing for small language models. Direct tensor edits, measured hill climbs and a Hugging Face workbench.
Image text to text model, used with transformers.
Image text to text model, used with gguf.
Closed-form, gradient-free weight-space interventions on snlucsb/netFound-small: representation geometry moves, nearest-centroid decisions do not.