FABLE decouples fine-grained fact anchoring in shallow Transformer layers from deeper text generation to improve specific fact access while preserving holistic editing performance.
Easyedit: An easy-to-use knowledge editing framework for large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
LOKI enables memory-free lifelong knowledge editing via HSIC-based dynamic layer selection and null-space constrained updates, reporting up to 14% higher average accuracy than prior methods.
LLMs prioritize task-appropriate reasoning over conflicting instructions, but reasoning types are linearly encoded in middle-to-late layers, allowing activation steering to raise instruction compliance by up to 29%.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
-
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
FABLE decouples fine-grained fact anchoring in shallow Transformer layers from deeper text generation to improve specific fact access while preserving holistic editing performance.
-
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
-
LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
LOKI enables memory-free lifelong knowledge editing via HSIC-based dynamic layer selection and null-space constrained updates, reporting up to 14% higher average accuracy than prior methods.
-
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
LLMs prioritize task-appropriate reasoning over conflicting instructions, but reasoning types are linearly encoded in middle-to-late layers, allowing activation steering to raise instruction compliance by up to 29%.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.