model-editing

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

Reproducible refusal-subspace editing and TP=2 deployment of DeepSeek V4 Flash 0731 on two DGX Sparks

[ACL 2024] An Easy-to-use Hallucination Detection Framework for LLMs.

[AAAI 2025 oral] Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit