Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 3526-3548
Abstract
Nan Xu, Fei Wang, Ben Zhou, Bangzheng Li, Chaowei Xiao, Muhao Chen. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Jailbreak and Guard Aligned Language Models With Only Few In-Context DemonstrationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
- Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks2024
- Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective2023
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- Large language models associate Muslims with violenceNature Machine Intelligence, 2021
- From Theory to Practice: The Application of Cognitive Load Theory to the Practice of MedicineAcademic Medicine, 2020
- Cognitive-Load Theory: Methods to Manage Working Memory Load in the Learning of Complex TasksCurrent Directions in Psychological Science, 2020
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models2020
- Dense Passage Retrieval for Open-Domain Question Answering2020
- The Use of Worked Examples as a Substitute for Problem Solving in Learning AlgebraCognition and Instruction, 1985