# The Inadequacy of Reinforcement Learning From Human Feedback—Radicalizing Large Language Models via Semantic Vulnerabilities

> Research article (IEEE Transactions on Cognitive and Developmental Systems, 2024) · cited 54× · AI/ML

**Wikidata**: [openalex:W4392908117](https://www.wikidata.org/wiki/openalex:W4392908117)  
**Source**: https://4ort.xyz/entity/the-inadequacy-of-reinforcement-learning-from-human-feedbackradicalizing-large-language-models-via-semantic-vulnerabilit