Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment. Xue, Z., Qi, Z., Liu, G., Chen, B., & Pedarsani, R. arXiv preprint arXiv:2603.11388, 2026. bibtex @article{xue2026deactivating,
title={Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment},
author={Xue, Zhiyu and Qi, Zimo and Liu, Guangliang and Chen, Bocheng and Pedarsani, Ramtin},
journal={arXiv preprint arXiv:2603.11388},
year={2026}
}
Downloads: 0
{"_id":"N6mhtNDM7iEGPKrTu","bibbaseid":"xue-qi-liu-chen-pedarsani-deactivatingrefusaltriggersunderstandingandmitigatingoverrefusalinsafetyalignment-2026","author_short":["Xue, Z.","Qi, Z.","Liu, G.","Chen, B.","Pedarsani, R."],"bibdata":{"bibtype":"article","type":"article","title":"Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment","author":[{"propositions":[],"lastnames":["Xue"],"firstnames":["Zhiyu"],"suffixes":[]},{"propositions":[],"lastnames":["Qi"],"firstnames":["Zimo"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Guangliang"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Bocheng"],"suffixes":[]},{"propositions":[],"lastnames":["Pedarsani"],"firstnames":["Ramtin"],"suffixes":[]}],"journal":"arXiv preprint arXiv:2603.11388","year":"2026","bibtex":"@article{xue2026deactivating,\n title={Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment},\n author={Xue, Zhiyu and Qi, Zimo and Liu, Guangliang and Chen, Bocheng and Pedarsani, Ramtin},\n journal={arXiv preprint arXiv:2603.11388},\n year={2026}\n}\n\n","author_short":["Xue, Z.","Qi, Z.","Liu, G.","Chen, B.","Pedarsani, R."],"key":"xue2026deactivating","id":"xue2026deactivating","bibbaseid":"xue-qi-liu-chen-pedarsani-deactivatingrefusaltriggersunderstandingandmitigatingoverrefusalinsafetyalignment-2026","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/network/files/v9iLSAgPxqijWtNb2","dataSources":["HQzSNhug84wo985ng"],"keywords":[],"search_terms":["deactivating","refusal","triggers","understanding","mitigating","overrefusal","safety","alignment","xue","qi","liu","chen","pedarsani"],"title":"Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment","year":2026}