Hwan Chang
4 papers · 2025–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(15)
❓
The Questioner
(2)
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(2)
Machine Learning
(2)
Natural Language Processing
(2)
Applications
(2)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Security & Privacy
(1)
Analysis
(1)
Application Areas
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Privacy
(1)
Keywords
large language model
(2)
question answering
(2)
privacy preservation
(1)
document retrieval
(1)
machine unlearning
(1)
model analysis
(1)
model interpretability
(1)
vision-language model
(1)
attention head
(1)
information leakage
(1)
retrieval-augmented generation
(1)
large vision-language model
(1)
open-domain question answering
(1)
llm safety
(1)
optical character recognition
(1)
retrieval head
(1)
indirect attack
(1)
syntactic similarity
(1)
hidden state probing
(1)
selective retrieval
(1)
Papers
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
EMNLP 2025
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
EMNLP 2025
Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
NAACL 2025
Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
ACL 2025