'Believe' is Strong but Subjective: Experimental Evidence from Hedging

Abstract

This paper contributes to the debate concerning whether the attitude verb believe has a weak or a strong semantics. According to Hawthorne et al. (2016), believe is weak and akin to the probability operator likely, typically receiving an “agent finds it more likely than not” interpretation. Alternatively, Koev (2019) proposes that believe conveys high certainty but qualifies this certainty as subjective or lacking evidence, in contrast with modals that convey high objective certainty, like sure (see also Lyons 1977; Kratzer 1981; Nuyts 2001; Papafragou 2006; Portner 2009). We focus on the use of believe as a hedge (e.g. I believe the Giants will win, but I’m not sure they will) as allegedly the most convincing argument for the weak view, and argue that, in fact, it favors the strong-but-subjective view. We show experimentally that the availability of the hedging use of believe is affected by certain grammatical and discourse factors. Experiment 1 reveals that participants rate hedging sentences with combinations of third person/past tense/embedded features as less natural than canonical first person/present tense/main clause forms. In turn, Experiment 2 reveals that hedging sentences with at-issue prejacents are judged as more natural than sentences in which the belief component is at-issue. The observed variability posits a challenge to the weak view, which establishes a purely logical contrast in modal strength between likelihood vs. certainty. However, it is in line with the strong-but-subjective view, which establishes a contrast in modal content between certainty without evidence vs. certainty with evidence and predicts a more restricted distribution of the hedging reading.