SOTAVerified

Model Editing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 193 papers

TitleStatusHype
NAACL2025 Tutorial: Adaptation of Large Language Models—0
Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation PatchingCode0
Efficient Model Editing with Task-Localized Sparse Fine-tuningCode0
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language ModelsCode0
BiasEdit: Debiasing Stereotyped Language Models via Model EditingCode1
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion ModelsCode1
Exploiting Edited Large Language Models as General Scientific Optimizers—0
GeoEdit: Geometric Knowledge Editing for Large Language Models—0
A Causal Lens for Evaluating Faithfulness Metrics—0
CoME: An Unlearning-based Approach to Conflict-free Model EditingCode0
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing—0
The Mirage of Model Editing: Revisiting Evaluation in the WildCode1
K-Edit: Language Model Editing with Contextual Knowledge Awareness—0
Reinforced Lifelong Editing for Language ModelsCode1
Injecting Universal Jailbreak Backdoors into LLMs in MinutesCode1
AnyEdit: Edit Any Knowledge Encoded in Language Models—0
Cross-Encoder Rediscovers a Semantic Variant of BM25—0
Position: Editing Large Language Models Poses Serious Safety Risks—0
Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable ApproachCode0
Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution—0
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach—0
SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation—0
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image ClassificationCode0
Concept-ROT: Poisoning Concepts in Large Language Models with Model EditingCode0
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models—0
Show:102550
← PrevPage 2 of 8Next →

No leaderboard results yet.