The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness. Varshney, N., Dolin, P., Seth, A., & Baral, C. arXiv preprint arXiv:2401.00287, ACL 2024 (Findings), 2024. bibtex @article{rrv2024chaosw,
title={The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness},
author={Varshney, Neeraj and Dolin, Pavel and Seth, Agastya and Baral, Chitta},
journal={arXiv preprint arXiv:2401.00287},
publisher="ACL 2024 (Findings)",
year={2024}
}
Downloads: 0
{"_id":"4wvL8rY7Pt9bNgg99","bibbaseid":"varshney-dolin-seth-baral-theartofdefendingasystematicevaluationandanalysisofllmdefensestrategiesonsafetyandoverdefensiveness-2024","author_short":["Varshney, N.","Dolin, P.","Seth, A.","Baral, C."],"bibdata":{"bibtype":"article","type":"article","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","author":[{"propositions":[],"lastnames":["Varshney"],"firstnames":["Neeraj"],"suffixes":[]},{"propositions":[],"lastnames":["Dolin"],"firstnames":["Pavel"],"suffixes":[]},{"propositions":[],"lastnames":["Seth"],"firstnames":["Agastya"],"suffixes":[]},{"propositions":[],"lastnames":["Baral"],"firstnames":["Chitta"],"suffixes":[]}],"journal":"arXiv preprint arXiv:2401.00287","publisher":"ACL 2024 (Findings)","year":"2024","bibtex":"@article{rrv2024chaosw,\n title={The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness},\n author={Varshney, Neeraj and Dolin, Pavel and Seth, Agastya and Baral, Chitta},\n journal={arXiv preprint arXiv:2401.00287},\n publisher=\"ACL 2024 (Findings)\",\n year={2024}\n}\n\n","author_short":["Varshney, N.","Dolin, P.","Seth, A.","Baral, C."],"key":"rrv2024chaosw-1","id":"rrv2024chaosw-1","bibbaseid":"varshney-dolin-seth-baral-theartofdefendingasystematicevaluationandanalysisofllmdefensestrategiesonsafetyandoverdefensiveness-2024","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://cogintlab-asu.github.io/cogint_bib.bib","dataSources":["qFKdMbFtP3HEjG9PQ"],"keywords":[],"search_terms":["art","defending","systematic","evaluation","analysis","llm","defense","strategies","safety","over","defensiveness","varshney","dolin","seth","baral"],"title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","year":2024}