A causal audit of LMLMs finds near-zero parametric leakage after deletion, with surviving correctness coming from retrieval artifacts in the database.
arXiv preprint arXiv:2305.13172 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
MetaKE unifies knowledge editing stages via bi-level optimization and a structural gradient proxy to improve the accuracy-editability trade-off over prior methods.
OR-VSKC provides 28,190 synthetic operating room images plus an expert subset to expose and reduce visual-semantic knowledge conflicts in multimodal models for surgical risk detection.
Introduces a benchmark using logical rules from knowledge graphs to generate multi-hop questions that evaluate whether knowledge edits in LLMs propagate to entailed facts, finding up to 24% performance gaps for methods like ROME and FT.
Distinguishable Deletion unifies knowledge erasure and refusal for LLM unlearning via an energy index that enforces boundaries during training and enables refusal at inference.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
HETA is a new attribution framework for decoder-only LLMs that combines semantic transition vectors, Hessian-based sensitivity scores, and KL divergence to produce more faithful and human-aligned token attributions than prior methods.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
No citing papers match the current filters.