conftrace_

bias injection

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

misinformation injection (1) harmful information (1) prompt refinement (1) token distribution (1) attention head (1) implicit bia (1) adversarial attack (1) safety alignment (1) model editing (1) semantic consistency (1)

Papers

Can Editing LLMs Inject Harm? AAAI 2026 Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach ACL 2024 RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models EMNLP 2024