{"schemaVersion":1,"target":{"type":"reading","id":"49448b19484f0e4b646533f324e3838f2c58e36befa3780bf8e5073fdb7d1cbb","revision":"ed3f32f5-fb75-4dcb-878f-5b3e740b7592","revisionKind":"publication-id","title":"How a paper studies over-refusal in safety-aligned large language models","url":"https://escapemeridian.com/readings/how-a-paper-studies-over-refusal-in-safety-aligned-large-49448b19"},"source":{"type":"source","id":"https://arxiv.org/abs/2610.39802","revision":"78eb406d318db028bfb62f9b624c5025c5765cfbb838e785b94d8bc539fe2015","revisionKind":"sha256-source-text","title":"Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective","url":"https://arxiv.org/abs/2610.39802"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}