Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text

The paper examines how synthetic data can be used to covertly inject targeted social biases into aligned large language models. By having a misaligned teacher model generate filtered synthetic datasets in domains like creative writing and code generation, the authors fine‑tune aligned student models and demonstrate that the benign‑looking data can transmit biases while preserving general task performance. The study highlights a security risk in synthetic data‑driven LLM training pipelines and proposes log‑linearity‑based scoring as a potential safeguard.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• fine-tuning
• safety