Underspecified LLM prompts cause fragile performance that doubles regression risk, and requirements-aware optimization improves average results by 4.8%.
accurate numerical values in summaries
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
-
What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
Underspecified LLM prompts cause fragile performance that doubles regression risk, and requirements-aware optimization improves average results by 4.8%.