Story

arxiv_cs_cl ยท Nov 18, 2026 ยท paper

Source brief

Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

arxiv.orgNov 18, 2026
original source linked

In brief

Jailbreak attempts and harmful prompts remain a challenge for the safe deployment of large language models. We study whether contrastively learned representations can support safety detection without training an addit...

Continues in

Large Language โ€” open the evidence trace โ†’

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items