ambiguity
Uncertainty about which model or which parameter values are correct—i.e., uncertainty about how much weight or probability to assign across competing models—distinct from within-model risk.
As defined in Lars Peter Hansen on Risk, Ambiguity, and Measurement
Where it comes up · 2
- Claimify: Extracting high-quality claims from language model outputs4 claims
- Lars Peter Hansen on Risk, Ambiguity, and Measurement1 claim
Most important claims · 5 of 5Search all claims for “ambiguity” →
- Uncertainty has three distinct components: risk (a fully specified model assigns probabilities to all future events), ambiguity (uncertainty about how much weight or confidence to place across multiple competing models or unknown parameters), and model misspecification (all models are wrong, requiring robustness to forms of misspecification you cannot fully identify).Lars Peter Hansen on Risk, Ambiguity, and Measurement
- Claimify's ability to determine whether ambiguity in a sentence can be resolved using context is a particularly unique and powerful aspect of the disambiguation stage.Claimify: Extracting high-quality claims from language model outputs
- When a language model generates the sentence 'the UN found that the resulting contaminated water caused many residents to fall ill, highlighting the need for improved water management,' a baseline system may miss the ambiguity about whether the author is stating a verifiable fact (that the UN found the need for improved water management) or adding their own interpretation.Claimify: Extracting high-quality claims from language model outputs
- Claimify breaks down claim extraction into three distinct stages: selection (filtering sentences without verifiable claims), disambiguation (detecting and resolving ambiguity), and decomposition (breaking sentences into simple factual statements).Claimify: Extracting high-quality claims from language model outputs
- Ambiguity in claim extraction refers to situations where multiple plausible interpretations of a sentence exist, and depending on which interpretation is chosen, a very different set of claims will result.Claimify: Extracting high-quality claims from language model outputs