LLMs detect harmful sentences in long inputs best at around 25% prevalence and when placed early, and worse when sparse, late, or implicit.
Title resolution pending
1 Pith paper cite this work, alongside 3 external citations. Polarity classification is still indexing.
1
Pith paper citing it
3
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs
LLMs detect harmful sentences in long inputs best at around 25% prevalence and when placed early, and worse when sparse, late, or implicit.