Yunzhi Yao
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16SkillNet: Create, Evaluate, and Connect AI Skills
arXiv 2026
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
arXiv 2026
Aligning Agentic World Models via Knowledgeable Experience Learning
arXiv 2026
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
arXiv 2026
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
arXiv 2026
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
arXiv 2025
LightMem: Lightweight and Efficient Memory-Augmented Generation
arXiv 2025
ReCode: Updating Code API Knowledge with Reinforcement Learning
arXiv 2025
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
arXiv 2025
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
arXiv 2025
Knowledge Circuits in Pretrained Transformers
arXiv 2024
Exploring Model Kinship for Merging Large Language Models
arXiv 2024
LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
arXiv 2023
Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
arXiv 2023
Unveiling the Pitfalls of Knowledge Editing for Large Language Models
arXiv 2023
Reasoning with Language Model Prompting: A Survey
arXiv 2022
Affiliations
Frequent co-authors
10from 16 papers