New preprints on data generation with LLMs and LLM's backdoor attack

In STAR, we propose to synthesize training data by structure-to-text generation using Large Language Models and we show that the generated data is even more effective than human-curated data instances to boost the low-resource event extraction performance.
In the new study about LLM’s backdoor attack, we demonstrate that an attacker can inject backdoors by issuing very few malicious instructions and control model behavior through data poisoning.

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung, P. Jeffrey Brantingham, Nanyun Peng, Wei Wang

AAAI, 2024

We propose STAR, a structure-to-text data generation method for complicated structure prediction tasks that first generates complicated event structures (Y) and then generates input passages (X), all with Large Language Models. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. We show that the data generated by STAR significantly improves the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data.

PDF Cite Code Poster DOI

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Jiashu Xu, Mingyu Derek Ma, Fei Wang, Chaowei Xiao, Muhao Chen

NAACL, 2024

Our studies demonstrate that an attacker can inject backdoors by issuing very few malicious instructions among thousands of gathered data and control model behavior through data poisoning. Through such instruction attacks, the attacker can achieve over 90% attack success rate across four commonly used NLP datasets, and cause persistent backdoors that are easily transferred to 15 diverse datasets zero-shot.

PDF Cite DOI