# Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings

arXiv: https://arxiv.org/abs/1606.06368 · HTML: https://mlsanity.com/paper/1606.06368/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2016.

## Built on by (most cited first, 7 of 7)

- [Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly](https://mlsanity.com/paper/2204.13631/) (2022)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation](https://mlsanity.com/paper/2311.08877/) (2023)
- [Selective Prediction via Training Dynamics](https://mlsanity.com/paper/2205.13532/) (2022)
- [ScatterShot: Interactive In-context Example Curation for Text Transformation](https://mlsanity.com/paper/2302.07346/) (2023)
- [Uncertainty Quantification on Clinical Trial Outcome Prediction](https://mlsanity.com/paper/2401.03482/) (2024)
- [UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification](https://mlsanity.com/paper/2210.15056/) (2022)

## Abstract (arXiv)

Can we train a system that, on any new input, either says "don't know" or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided our model family is well-specified. Specifically, we introduce the unanimity principle: only predict when all models consistent with the training data predict the same output. We operationalize this principle for semantic parsing, the task of mapping utterances to logical forms. We develop a simple, efficient method that reasons over the infinite set of all consistent models by only checking two of the models. We prove that our method obtains 100% precision even with a modest amount of training data from a possibly adversarial distribution. Empirically, we demonstrate the effectiveness of our approach on the standard GeoQuery dataset.