When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Paper • 2605.30219 • Published • 26
Xu Ziwen
xzwnlp
AI & ML interests
None yet
Recent Activity
upvoted a paper 29 days ago
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning upvoted a paper 30 days ago
MemTrace: Tracing and Attributing Errors in Large Language Model Memory SystemsOrganizations
upvoted 2
papers 29 days ago
upvoted a paper 30 days ago
upvoted a paper about 1 month ago
authored 9
papers 3 months ago
A Comprehensive Study of Knowledge Editing for Large Language Models
Paper • 2401.01286 • Published • 21
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models
Paper • 2402.03049 • Published • 1
Detoxifying Large Language Models via Knowledge Editing
Paper • 2403.14472 • Published • 3
Knowledge Circuits in Pretrained Transformers
Paper • 2405.17969 • Published • 1
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Paper • 2405.14768 • Published • 1
Automating Steering for Safe Multimodal Large Language Models
Paper • 2507.13255 • Published • 4
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper • 2510.18866 • Published • 116
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Paper • 2602.02343 • Published • 13
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Paper • 2603.02578 • Published • 25
upvoted 2
articles 3 months ago
Article
Take Control of What Your LLM Knows and Does — with the EasyEdit Tool Series
xzwnlp
• • 9 Article
Making LLMs Truly Remember You | LightMem: Lightweight and Efficient Memory-Augmented Generation
xzwnlp
• • 5 liked a
dataset 4 months ago
published a
dataset 4 months ago
updated a
dataset 4 months ago
upvoted a paper 4 months ago
published an article 4 months ago
Article
让大模型真正「记住你」｜LightMem：轻量高效的记忆增强生成框架
xzwnlp
• • 1