PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data

Tingchen Fu; Mrinank Sharma; Philip Torr; Shay B Cohen; David Krueger; Fazl Barez

2025 ICML ICML 2025

PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Tingchen Fu, Mrinank Sharma, Philip Torr, Shay B Cohen, David Krueger, Fazl Barez

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Learning Types > Adversarial Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

robustness preference data large language model poisoning attack vulnerability

Download PDF