HWANCHANG's picture

2 6 1

HWANCHANG

HwanChang0106

·

AI & ML interests

None yet

Organizations

None yet

authored 3 papers 3 months ago

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

Paper • 2410.13339 • Published Oct 17, 2024

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads

Paper • 2505.15865 • Published May 21 • 4

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents

Paper • 2509.22830 • Published Sep 26 • 4

authored a paper 7 months ago

Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering

Paper • 2505.15805 • Published May 21 • 3