Reluctant acceptance of the literal truth: Eye tracking in the Covered Box Paradigm Florian Schwarz — University of Pennsylvania Cory Bill — CCD/Macquarie University Jacopo Romoli — Ulster University Abstract. Since Bott and Noveck (2004), there has been an ongoing discussion about whether scalar implicatures are delayed in online processing relative to literal meaning. Bott and Noveck (2004) provided Reaction Time evidence for such a delay, replicated in a number of later variations of their study (e.g., Bott et al., 2012). Breheny et al. (2006) found corresponding delays in self- paced reading. More recently, the issue has been investigated using the visual world paradigm, where results have been more mixed. Huang and Snedeker (2009, and subsequent work) have found delays for eye movements based on the ‘not all’ implicature of ‘some.’ But various others, (e.g., Grodner et al. (2010), Breheny et al. (2013), and Degen and Tanenhaus (2011)), report results which they argue show that implicatures are available immediately. Schwarz et al. (2015) added another angle to this picture, by using a sentence picture matching task using a Covered Picture (or Covered Box; henceforth CB; Huang et al., 2013), that allowed RT comparisons both within ac- ceptance (target) and rejection (CB) responses. While replicating the delay for implicature-based rejection responses, they find the reverse pattern for acceptance responses, with faster RTs for implicature-compatible conditions. They propose that delays associated with literal acceptances and implicature-based rejections result from a conflict between the two possible interpretations, rather than reflecting a cost of implicature-calculation. The present experiment extends this ap- proach beyond RTs by combining Visual World eye-tracking with the CB paradigm. The results a) are consistent with the notion that both literal and implicature interpretations are available in par- allel; b) show that literal acceptances are nonetheless only provided reluctantly, presumably due to a preference for implicature meanings, in line with Schwarz et al’s proposal; and c) suggest that for both literal acceptances and implicature-based rejections, there is a competition effect between the two interpretations. In addition, the RT data display an implicature-based block-priming effect, suggesting that the resolution of this conflict can be sped up through repeated task-exposure. Keywords: scalar implicatures, processing, visual world eye tracking 1. Introduction A major tenet in the modern study of linguistic semantics and pragmatics is that while speakers may perceive the meaning of a given utterance in its totality, it is actually a complex construct out of various distinct ingredients that constitute different aspects of meaning, such as literal/truth- conditional content, conversational implicatures, and presuppositions. One key theoretical ques- tion is to understand what aspects of meaning should be differentiated, and what theoretical prop- erties they have. From the perspective of online language processing, an additional question is how these various aspects of meaning arise in real time and how they are combined into the perceived