Large Language Models (LLMs) can engage in human-looking conversational exchanges. Although conversations can elicit trust between users and LLMs, scarce empirical research has examined trust formation in human-LLM contexts, beyond LLMs' trustworthiness or human trust in AI in general. Here, we introduce the Trust-In-LLMs Index (TILLMI) as a new framework to measure individuals' trust in LLMs, extending McAllister's cognitive and affective trust dimensions to LLM-human interactions. We developed TILLMI as a psychometric scale, prototyped with a novel protocol we called LLM-simulated validity. The LLM-based scale was then validated in a sample of 1,000 US respondents. Exploratory Factor Analysis identified a two-factor structure. Two items were then removed due to redundancy, yielding a final 6-item scale with a 2-factor structure. Confirmatory Factor Analysis on a separate subsample showed strong model fit ($CFI = .995$, $TLI = .991$, $RMSEA = .046$, $p_{X^2} > .05$). Convergent validity analysis revealed that trust in LLMs correlated positively with openness to experience, extraversion, and cognitive flexibility, but negatively with neuroticism. Based on these findings, we interpreted TILLMI's factors as "closeness with LLMs" (affective dimension) and "reliance on LLMs" (cognitive dimension). Younger males exhibited higher closeness with- and reliance on LLMs compared to older women. Individuals with no direct experience with LLMs exhibited lower levels of trust compared to LLMs' users. These findings offer a novel empirical foundation for measuring trust in AI-driven verbal communication, informing responsible design, and fostering balanced human-AI collaboration.

However, a critical gap exists in the lack of generalizable and accurate specialized measurement tools Trust plays a crucial role not only in fostering cooperation, for assessing affective trust in the context of AI, especially efficiency, and productivity in human relationships (Brainov with the enhanced and nuanced capabilities of LLMs. This and Sandholm 1999) but also is essential for the effective highlights a need for a better measurement scale for affective use and acceptance of computing and automated systems, trust to gain a deeper understanding of how trust dynamics including computers (Madsen and Gregor 2000), automation function, particularly in the context of emotionally intelligent (Lee and See 2004), robots (Hancock et al. 2011), and AI. AI technologies (Kumar 2021), with a deficit in trust potentially In this paper, we introduce a 27-item semantic differential causing rejection of these technologies (Glikson and scale for assessing cognitive and affective trust in AI, Woolley 2020). The two-dimensional model of trust, encompassing aiding researchers and designers in understanding and improving both cognitive and affective dimensions proposed human-AI interactions. Our motivation and scale and studied in interpersonal relationship studies (McAllister development process is based on a long strand of prior research 1995; Johnson and Grayson 2005; Parayitam and Dooley on the cognitive-affective construct of trust that has 2009; Morrow Jr, Hansen, and Pearson 2004), have been shown to be important in interpersonal trust in organizations, been adopted in studying trust in human-computer interactions, human trust in conventional technology and automation, particularly with human-like technologies (Hu, Lu and more recently in trust towards AI.

Predicting the collaboration likelihood and measuring cognitive trust to AI systems is more important than ever. To do that, previous research mostly focus solely on the model features (e.g., accuracy, confidence) and ignore the human factor. To address that, we propose several decision-making similarity measures based on divergence metrics (e.g., KL, JSD) calculated over the labels acquired from humans and a wide range of models. We conduct a user study on a textual entailment task, where the users are provided with soft labels from various models and asked to pick the closest option to them. The users are then shown the similarities/differences to their most similar model and are surveyed for their likelihood of collaboration and cognitive trust to the selected system. Finally, we qualitatively and quantitatively analyze the relation between the proposed decision-making similarity measures and the survey results. We find that people tend to collaborate with their most similar models -- measured via JSD -- yet this collaboration does not necessarily imply a similar level of cognitive trust. We release all resources related to the user study (e.g., design, outputs), models, and metrics at our repo.

Automated vehicles (AVs) are social robots that can potentially benefit our society. According to the existing literature, AV explanations can promote passengers' trust by reducing the uncertainty associated with the AV's reasoning and actions. However, the literature on AV explanations and trust has failed to consider how the type of trust - cognitive versus affective - might alter this relationship. Yet, the existing literature has shown that the implications associated with trust vary widely depending on whether it is cognitive or affective. To address this shortcoming and better understand the impacts of explanations on trust in AVs, we designed a study to investigate the effectiveness of explanations on both cognitive and affective trust. We expect these results to be of great significance in designing AV explanations to promote AV trust.

We consider the setting of stochastic multiagent systems and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a cognitive notion of trust defined as a subjective evaluation that agent A makes about agent B's ability to complete a task, which in turn may lead to a decision by A to rely on B. We propose a probabilistic rational temporal logic PRTL*, which extends the logic PCTL* with reasoning about mental attitudes (beliefs, goals and intentions), and includes novel operators that can express concepts of social trust such as competence, disposition and dependence. The logic can express, for example, that "agent A will eventually trust agent B with probability at least p that B will be have in a way that ensures the successful completion of a given task". We study the complexity of the automated verification problem and, while the general problem is undecidable, we identify restrictions on the logic and the system that result in decidable, or even tractable, subproblems.