Appending visible descending countdown markers to the prompt makes off-the-shelf LLMs hit exact word or character targets far more often, with exact-match rates reaching 30 to 96 percent across four benchmarks, eleven models, and two languages.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs
Appending visible descending countdown markers to the prompt makes off-the-shelf LLMs hit exact word or character targets far more often, with exact-match rates reaching 30 to 96 percent across four benchmarks, eleven models, and two languages.