https://github.com/ABi-dot/Kedkg
공식 코드Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Papers with Code 아카이브
Model Editing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Aries-chen/MedEditBench
공식 코드Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing
https://github.com/Betswish/Cross-Lingual-Consistency
공식 코드Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
https://github.com/BobXWu/AKEW
공식 코드https://github.com/ENSCMA2/flextape
공식 코드"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
https://github.com/Lyz1213/BadEdit
공식 코드https://github.com/MMKE-Bench-ICLR/MMKE-Bench
공식 코드MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
https://github.com/PinzhengWang322/Reveal_Attention_Drift
공식 코드Revealing and Mitigating Over-Attention in Knowledge Editing
https://github.com/TrustedLLM/UnKE
공식 코드Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
https://github.com/XZhang00/LU-LAFNs
공식 코드Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
https://github.com/Ymm-cll/UniErase
공식 코드UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
https://github.com/Zhow01/S2RKE
공식 코드https://github.com/acerkoo/disco
공식 코드Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
https://github.com/aengusl/latent-adversarial-training
공식 코드Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
https://github.com/ai4life-group/splice
공식 코드Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
https://github.com/alessiogalatolo/diekae
공식 코드https://github.com/amodaresi/memllm
공식 코드MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
https://github.com/anshitag/memit_csk
공식 코드https://github.com/apartresearch/specificityplus
공식 코드Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
https://github.com/applied-machine-learning-lab/mm4ke
공식 코드https://github.com/arnab-api/romba
공식 코드https://github.com/arvid-pku/atoke
공식 코드History Matters: Temporal Knowledge Editing in Large Language Model
https://github.com/asdfo123/scedit
공식 코드https://github.com/au-revoir/model-editing-ft
공식 코드https://github.com/bahjat-kawar/time-diffusion
공식 코드Editing Implicit Assumptions in Text-to-Image Diffusion Models
https://github.com/baixianghuang/behavior-edit
공식 코드Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
https://github.com/bboylyg/expose-before-you-defend
공식 코드Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
https://github.com/bebr2/editcot
공식 코드https://github.com/beepkh/unike
공식 코드Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
https://github.com/bigai-ai/ICE
공식 코드In-Context Editing: Learning Knowledge from Self-Induced Distributions
https://github.com/bruthyu/melo
공식 코드MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
https://github.com/byronbbl/deck
공식 코드Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
https://github.com/cap-ntu/ML-Model-CI
공식 코드ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
https://github.com/caskcsg/lyaplock
공식 코드LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
https://github.com/changchangsun/forget-vector
공식 코드https://github.com/chenhuihu/knowledge_in_superposition
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.