conftrace_

bias generalization

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

ideological manipulation (1) instruction-tuning data (1) large language model (1) poisoned training data (1) ideological bia (1) instruction tuning (1) data poisoning (1)

Papers

How Susceptible are Large Language Models to Ideological Manipulation? EMNLP 2024