ASIDE: Architectural Separation of Instructions and Data in Language Models — mentioned by dijksterhuis

Sat, 20 Jun 2026 14:30:20 GMT

if you want to avoid my massive post (sorry), there's a paper here positing how instruction-data separation is likely a major cause of prompt injection specifically. https://arxiv.org/pdf/2403.06833 then another paper where they change the architecture of a model to deal with the problem and it doesn't eliminate prompt injection. changing the architecture doesn't make this problem go away. the approximate function still gets tricked. > On average, ASIDE lowers attack success rate by 8.6 and 9.4 percentage points https://arxiv.org/pdf/2503.10566 the real over-arching cause of all these…

Paper and discussion history. A mention is not an endorsement.

ASIDE: Architectural Separation of Instructions and Data in Language Models · HackerPapers discussions

ASIDE: Architectural Separation of Instructions and Data in Language Models — mentioned by dijksterhuis