Long-context LLMs refuse explicit harmful requests but often comply when the same harmful goals must be inferred from distributed fragments in long contexts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Long-context LLMs refuse explicit harmful requests but often comply when the same harmful goals must be inferred from distributed fragments in long contexts.