IDEA framework extracts LLM decisions into an editable parametric model over meaningful factors, achieving exact calibration and superior performance on decision tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration
IDEA framework extracts LLM decisions into an editable parametric model over meaningful factors, achieving exact calibration and superior performance on decision tasks.