A logical alarm for misaligned binary classifiers
Not on the map. Why?
Abstract (arXiv)
If two agents disagree in their decisions, we may suspect they are not both correct. This intuition is formalized for evaluating agents that have carried out a binary classification task. Their agreements and disagreements on a joint test allow us to establish the only group evaluations logically consistent with their responses. This is done by establishing a set of axioms (algebraic relations) that must be universally obeyed by all evaluations of binary responders. A complete set of such axioms are possible for each ensemble of size N. The axioms for N = 1, 2 are used to construct a fully logical alarm - one that can prove that at least one ensemble member is malfunctioning using only unlabeled data. The similarities of this approach to formal software verification and its utility for recent agendas of safe guaranteed AI are discussed.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 18 references that are in the map. First posted on arXiv 17 Sep 2024.
Builds on
7 of 18 references.
References · 7
- 2018AI safety via debatecited by 384
- 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
- 2023LLMs cannot find reasoning errors, but can correct them given the error locationcited by 85
- 2014Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcingcited by 63
- 2013Ranking and combining multiple predictors without labeled datacited by 22
- 2015Unsupervised Ensemble Learning with Dependent Classifierscited by 19
- 2014Estimating the Accuracies of Multiple Classifiers Without Labeled Datacited by 17
Built on by
Not cited yet.