Chipkkang9's AI Security Research Lab.

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Tags Decoding

Tag

Decoding 1

[PaRev] NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection May 8, 2026

Recently Updated

[NetSec] Understanding TLS, PKI, and the Post-Quantum Transition
[PaRev] INFA-Guard: Infection-Aware MAS Safeguarding
[PaRev] NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection
[PaRev] On the Role of Attention Heads in Large Language Models Safety
[PaRev] Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

Trending Tags

AI LLM Safety Agent Security Multi-Agent Systems Graph Neural Network Model Activation Steering Attention Cryptography

© 2026 chipkkang9(Sanghyeon Park). Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

AI LLM Safety Agent Security Multi-Agent Systems Graph Neural Network Model Activation Steering Attention Cryptography

A new version of content is available.