Optimal conditioning sequences for sequence predictors are often unintuitive, better explained by pretraining distribution than task similarity, and popular demonstration-based prompts are frequently suboptimal even under exhaustive search.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why is prompting hard? Understanding prompts on binary sequence predictors
Optimal conditioning sequences for sequence predictors are often unintuitive, better explained by pretraining distribution than task similarity, and popular demonstration-based prompts are frequently suboptimal even under exhaustive search.