iPOE generates and optimizes annotation guidelines from explanations to produce interpretable prompts, reporting up to 39% gains over baselines on four datasets with LLM explanations substituting for human ones.
A Rose by Any Other Name: LLM -Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Softer label and rationale representations outperform hard ones on predictive, distributional, plausibility, faithfulness, and complexity metrics when models are re-implemented across representation spaces in hate speech detection.
citing papers explorer
-
iPOE: Interpretable Prompt Optimization via Explanations
iPOE generates and optimizes annotation guidelines from explanations to produce interpretable prompts, reporting up to 39% gains over baselines on four datasets with LLM explanations substituting for human ones.
-
Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
Softer label and rationale representations outperform hard ones on predictive, distributional, plausibility, faithfulness, and complexity metrics when models are re-implemented across representation spaces in hate speech detection.