Trust in AI

Follow this topic Ask about this topic

Trust in AI research studies how people judge AI systems and decide whether to accept, check, or delegate decisions to them, as well as how agents and institutions can verify one another. Researchers use controlled user studies, surveys, behavioral measures of reliance, and benchmarks, alongside methods such as uncertainty calibration, evidence-linked explanations, provenance records, and reputation or access-control protocols. Work spans settings including healthcare, education, information seeking, human-robot teams, and autonomous agents, where both system performance and interaction design shape trust. A central tension is that explanations, confidence signals, and warnings can change perceived trust without improving users’ ability to spot errors or rely appropriately, so evaluation must separate trust from accuracy, verification, and outcomes.

Latest papers

175 papers21 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

Mar 13, 2026

Human-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts

Integrating Large Language Models (LLMs) into business process management tools promises to democratize Business Process Model and Notation (BPMN) modeling for non-experts. While automated frameworks assess syntactic and semantic quality, they miss human factors like trust, usability, and professional alignment. We conducted a mixed-methods evaluation of our proposed solution, an LLM-powered BPMN copilot, with five process modeling experts using focus groups and standardized questionnaires. Our findings reveal a critical tension between acceptable perceived usability (mean CUQ score: 67.2/100) and notably lower trust (mean score: 48.8%), with reliability rated as the most critical concern (M=1.8/5). Furthermore, we identified output-quality issues, prompting difficulties, and a need for the LLM to ask more in-depth clarifying questions about the process. We envision five use cases ranging from domain-expert support to enterprise quality assurance. We demonstrate the necessity of human-centered evaluation complementing automated benchmarking for LLM modeling agents.

Chantale Lauer, Peter Pfeiffer, Nijat Mehdiyev

Saarland University, Saarbrücken, Saarland, Germany · German Research Institute for Artificial Intelligence, Saarbrücken, Saarland, Germany · 5Plus GmbH, Würzburg, Bavaria, Germany

Business Process Modeling LLM Agent Evaluation Trust in AI LLM Reliability Human-in-the-Loop Evaluation

Mar 12, 2026

Examining Users' Behavioural Intention to Use OpenClaw Through the Cognition--Affect--Conation Framework

This study examines users' behavioural intention to use OpenClaw through the Cognition--Affect--Conation (CAC) framework. The research investigates how cognitive perceptions of the system influence affective responses and subsequently shape behavioural intention. Enabling factors include perceived personalisation, perceived intelligence, and relative advantage, while inhibiting factors include privacy concern, algorithmic opacity, and perceived risk. Survey data from 436 OpenClaw users were analysed using structural equation modelling. The results show that positive perceptions strengthen users' attitudes toward OpenClaw, which increase behavioural intention, whereas negative perceptions increase distrust and reduce intention to use the system. The study provides insights into the psychological mechanisms influencing the adoption of autonomous AI agents.

Yiran Du

University of Cambridge

Mar 10, 2026

Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity

LLMs offer new creative possibilities for writers but also raise concerns about authenticity and reader trust, particularly when AI involvement is disclosed. Prior research has largely framed this as an issue of transparency and provenance, emphasizing the disclosure of human-AI interaction traces that account for how much the AI wrote and what the human did. Yet such audit-oriented disclosures may risk reducing creative collaboration to quantification and surveillance. In this position paper, we argue for a different lens by exploring how human-AI interaction traces might instead function as expressive artifacts that foreground the meaning-making inherent in human-AI collaboration. Drawing inspiration from blackout poetry, we frame AI-generated text as found material through which writers' acts of curation and reinterpretation become inscribed atop the AI's original output. In this way, we suggest that designing interaction traces as aesthetic artifacts may help readers better appreciate and trust writers' creative contributions in AI-assisted writing.

Syemin Park, Soobin Park, Youn-kyung Lim

Department of Industrial Design, KAIST, Republic of Korea

Human-AI Interaction Human-AI Co-Creation Trust in AI Computational Creativity

Mar 10, 2026

Stability of AI Governance Systems: A Coupled Dynamics Model of Public Trust and Social Disruptions

AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust in algorithmic institutions dissipate and when they grow into collapse. Stability refers here to asymptotic recovery from finite state perturbations under fixed structural parameters. We address this gap by developing a mathematical framework for institutional trust stability that couples a Friedkin-Johnsen opinion dynamics process with a Hawkes-inspired intensity process for AI controversies. Motivated by the Computers-Are-Social-Actors literature and recent studies of trust in large language models, this bidirectional coupling reveals that governance stability depends on the structural architecture of the information environment rather than absolute trust levels. We derive an exact spectral stability criterion delineating resilience from collapse, demonstrating how event self-excitation and memory persistence systematically narrow the stable parameter regime. Our structural analysis yields four counterintuitive structural implications: high-trust systems can be structurally fragile, low-trust environments can be structurally stable, dynamical stability neither measures nor guarantees algorithmic fairness or legitimacy, and network topology reshapes equilibrium heterogeneity while its effect on spectral stability is uniformly bounded in an explicit memory-dominated regime. Governance assessment should therefore pair normative evaluation of harms and fairness with structural analysis of recoverability, rather than treating either as a proxy for the other.

Jiaqi Lai, Hou Liang, Weihong Huang

Nanyang Technological University, Singapore

Hawkes Processes AI Governance Trust in AI

Mar 9, 2026

Trust via Reputation of Conviction

The question of knowledge, truth and trust is explored via a mathematical formulation of claims and sources. We define truth as the reproducibly perceived subset of knowledge, formalize sources as having both generative and discriminative roles, and develop a framework for reputation grounded in the conviction -- the likelihood that a source's stance is vindicated by independent consensus. We argue that conviction, rather than correctness or faithfulness, is the principled basis for trust: it is regime-independent, rewards genuine contribution, and demands the transparent and self-sufficient perceptions that make external verification possible. We formalize reputation as the expected weighted signed conviction over a realm of claims, characterize its behavior across source-claim regimes, and identify continuous verification as both a theoretical necessity and a practical mechanism through which reputation accrues. The framework is applied to AI agents, which are identified as capable but error-prone sources for whom verifiable conviction and continuously accrued reputation constitute the only robust foundation for trust.

Aravind R. Iyengar

Trust in AI Claim Verification

Mar 8, 2026

"Better Ask for Forgiveness than Permission": Practices and Policies of AI Disclosure in Freelance Work

The growing use of AI applications among freelance workers is reshaping trust and relationships with clients. This paper investigates how both workers and clients perceive AI use and disclosure in the freelance economy through a three-stage study: interviews with workers and two survey studies with workers and clients. Findings first reveal a key expectation gap around disclosure: Workers often adopt passive disclosure practices, revealing AI use only when asked, as they assume clients can already detect it. Clients, however, are far less confident in recognizing AI-assisted work and prefer proactive disclosure. A second finding highlights the role of unclear or absent client AI policies, which leave workers consistently misinterpreting clients' expectations for AI use and disclosure. Together, these gaps point to the need for clearer guidelines and practices for AI disclosure. Insights extend beyond freelancing, offering implications for trust, accountability, and policy design in other AI-mediated work domains.

Angel Hsing-Chi Hwang, Senya Wong, Baixiao Chen +2

University of Southern California · Emory University · IBM Research

AI Use Disclosure AI and Labor Trust in AI AI Governance

Mar 6, 2026

Evaluating LLM Alignment With Human Trust Models

Trust plays a pivotal role in enabling effective cooperation, reducing uncertainty, and guiding decision-making in both human interactions and multi-agent systems. Although it is significant, there is limited understanding of how large language models (LLMs) internally conceptualize and reason about trust. This work presents a white-box analysis of trust representation in EleutherAI/gpt-j-6B, using contrastive prompting to generate embedding vectors within the activation space of the LLM for diadic trust and related interpersonal relationship attributes. We first identified trust-related concepts from five established human trust models. We then determined a threshold for significant conceptual alignment by computing pairwise cosine similarities across 60 general emotional concepts. Then we measured the cosine similarities between the LLM's internal representation of trust and the derived trust-related concepts. Our results show that the internal trust representation of EleutherAI/gpt-j-6B aligns most closely with the Castelfranchi socio-cognitive model, followed by the Marsh Model. These findings indicate that LLMs encode socio-cognitive constructs in their activation space in ways that support meaningful comparative analyses, inform theories of social cognition, and support the design of human-AI collaborative systems.

Anushka Debnath, Stephen Cranefield, Bastin Tony Roy Savarimuthu +1

School of Computing, University of Otago, New Zealand · IRIT, CNRS, Toulouse University, France

Trust in AI LLM Interpretability

Mar 5, 2026

Not All Trust is the Same: Effects of Decision Workflow and Explanations in Human-AI Decision Making

A central challenge in AI-assisted decision making is achieving warranted, well-calibrated trust. Both overtrust (accepting incorrect AI recommendations) and undertrust (rejecting correct advice) should be prevented. Prior studies differ in the design of the decision workflow - whether users see the AI suggestion immediately (1-step setup) or have to submit a first decision beforehand (2-step setup) -, and in how trust is measured - through self-reports or as behavioral trust, that is, reliance. We examined the effects and interactions of (a) the type of decision workflow, (b) the presence of explanations, and (c) users' domain knowledge and prior AI experience. We compared reported trust, reliance (agreement rate and switch rate), and overreliance. Results showed no evidence that a 2-step setup reduces overreliance. The decision workflow also did not directly affect self-reported trust, but there was a crossover interaction effect with domain knowledge and explanations, suggesting that the effects of explanations alone may not generalize across workflow setups. Finally, our findings confirm that reported trust and reliance behavior are distinct constructs that should be evaluated separately in AI-assisted decision making.

Laura Spillner, Rachel Ringe, Robert Porzel +1

Digital Media Lab, University of Bremen, Germany

AI-Assisted Decision Making Trust in AI Human-AI Decision Making Explainability Evaluation

Mar 3, 2026

Architecting Trust in Artificial Epistemic Agents

Large language models increasingly function as epistemic agents -- entities that can 1) autonomously pursue epistemic goals and 2) actively shape our shared knowledge environment. They curate the information we receive, often supplanting traditional search-based methods, and are frequently used to generate both personal and deeply specialized advice. How they perform these functions, including whether they are reliable and properly calibrated to both individual and collective epistemic norms, is therefore highly consequential for the choices we make. We argue that the potential impact of epistemic AI agents on practices of knowledge creation, curation and synthesis, particularly in the context of complex multi-agent interactions, creates new informational interdependencies that necessitate a fundamental shift in evaluation and governance of AI. While a well-calibrated ecosystem could augment human judgment and collective decision-making, poorly aligned agents risk causing cognitive deskilling and epistemic drift, making the calibration of these models to human norms a high-stakes necessity. To ensure a beneficial human-AI knowledge ecosystem, we propose a framework centered on building and cultivating the trustworthiness of epistemic AI agents; aligning AI these agents with human epistemic goals; and reinforcing the surrounding socio-epistemic infrastructure. In this context, trustworthy AI agents must demonstrate epistemic competence, robust falsifiability, and epistemically virtuous behaviors, supported by technical provenance systems and "knowledge sanctuaries" designed to protect human resilience. This normative roadmap provides a path toward ensuring that future AI systems act as reliable partners in a robust and inclusive knowledge ecosystem.

Nahema Marchal, Stephanie Chan, Matija Franklin +5

Google DeepMind · Google Research

Trust in AI AI Agent Governance AI Agent Reliability

Mar 2, 2026

Strategic Advice in the Age of Personal AI

Personal AI assistants are changing how individuals use advice. We study how an advisor should design its recommendation in anticipation of stochastic consultation with personal AI whose recommendation is predictable. Personal AI enters through two dimensions: consultation probability and relative trust, which captures the relative influence personal AI receives when consulted. In the baseline model, the advisor optimally counteracts the personal AI signal. Counteraction increases with consultation probability but is hump-shaped in relative trust. The advisor's minimized loss is hump-shaped in consultation probability, vanishing when personal AI is never or always consulted. Greater relative trust in personal AI increases the irreducible loss arising from stochastic consultation. We extend the analysis to partial predictability and costly recommendation adjustment, characterizing their effects on optimal recommendations and minimized loss. The framework also accommodates richer information structures, including settings in which personal AI is perceived as having access to private information relevant to the task. We introduce an online forecasting experiment that examines how participants obtain personal AI advice and combine it with an advisor's recommendation and their initial judgments. Participants place weight on all three inputs. When access requires an additional action, some participants do not seek personal AI advice, while some others attempt to obtain it without success. Together, these findings highlight two distinct aspects of personal AI use: whether advice is obtained and how much weight it receives when available.

Yueyang Liu, Wichinpong Park Sinchaisri

1Jones Graduate School of Business, Rice University · 2Haas School of Business, University of California, Berkeley

Trust in AI Human-AI Decision Making Personal AI Agents

Mar 1, 2026

Anthropomorphism and Trust in Human-Large Language Model interactions

With large language models (LLMs) becoming increasingly prevalent in daily life, so too has the tendency to attribute to them human-like minds and emotions, or anthropomorphize them. Here, we investigate dimensions people use to anthropomorphize and attribute trust toward LLMs across more than 2,000 human-LLM interactions. Participants (N=115) engaged with LLM chatbots systematically varied in warmth (friendliness), competence (capability, coherence), and empathy (cognitive and affective). Warmth and cognitive empathy significantly predicted perceptions on all outcomes (perceived anthropomorphism, trust, similarity, relational closeness, frustration, usefulness), while competence predicted all outcomes except for anthropomorphism. Affective empathy primarily predicted perceived relational measures, but did not predict the epistemic outcomes. Topic sub-analyses showed that more subjective, personally relevant topics (e.g., relationship advice) amplified these effects, producing greater human-likeness and relational connection with the LLM than did objective topics. Together, these findings reveal that warmth, competence, and empathy are key dimensions through which people attribute relational and epistemic perceptions to artificial agents.

Akila Kadambi, Ylenia D'Elia, Tanishka Shah +8

Brain and Creativity Institute, Dornsife College of Letters, Arts and Sciences, University of Southern California, Los Angeles, CA, USA · USC Mrs. T.H. Chan Division of Occupational Science and Occupational Therapy, University of Southern California, Los Angeles, CA, USA · Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA +2

Anthropomorphism in AI Human-AI Interaction Trust in AI Conversational Agents

Mar 1, 2026

Agent-Based Simulation of Trust Development in Human-Robot Teams: An Empirically-Validated Framework

This paper presents an empirically grounded agent-based model capturing trust dynamics, workload distribution, and collaborative performance in human-robot teams. The model, implemented in NetLogo 6.4.0, simulates teams of 2--10 agents performing tasks of varying complexity. We validate against Hancock et al.'s (2021) meta-analysis, achieving interval validity for 4 of 8 trust antecedent categories and strong ordinal validity (Spearman \r{ho}=0.833ρ= 0.833 \r{ho}=0.833). Sensitivity analysis using OFAT and full factorial designs (n=50n = 50 n=50 replications per condition) reveals robot reliability exhibits the strongest effect on trust (η2=0.35η^2 = 0.35 η2=0.35) and dominates task success (η2=0.93η^2 = 0.93 η2=0.93) and productivity (η2=0.89η^2 = 0.89 η2=0.89), consistent with meta-analytic findings. Trust asymmetry ratios ranged from 0.07 to 0.55 -- below the meta-analytic benchmark of 1.50 -- revealing that per-event asymmetry does not guarantee cumulative asymmetry when trust repair mechanisms remain active. Scenario analysis uncovered trust-performance decoupling: the Trust Recovery scenario achieved the highest productivity (4.29) despite the lowest trust (38.2), while the Unreliable Robot scenario produced the highest trust (73.2) despite the lowest task success (33.4%), establishing calibration error as a critical diagnostic distinct from trust magnitude. Factorial ANOVA confirmed significant main effects for reliability, transparency, communication, and collaboration (p<.001p < .001 p<.001), explaining 45.4% of trust variance. The open-source implementation provides an evidence-based tool for identifying overtrust and undertrust conditions prior to deployment.

Ravi Kalluri

College of Professional Studies, Northeastern University – San Jose, California, United States

Trust in HRI Human-Robot Collaboration Human-Robot Interaction Trust in AI Agent-Based Modeling

Feb 27, 2026

Advancing Trustworthy AI in Healthcare Through Meta-Research: Results of an Interdisciplinary Design-Thinking Workshop

Meta-research and Trustworthy AI (TAI) share common goals, namely improving evidence, robustness, and transparency, yet there is very little interplay between the two fields. To investigate the potential benefits of closer collaboration between the domains of TAI in healthcare and meta-research, we convened an interdisciplinary workshop funded by the Volkswagen Foundation in February 2025. The workshop aimed to collaboratively examine key challenges in translating AI ethics principles into practice and to identify potential solutions informed by meta-research approaches. A Design Thinking-informed co-creation approach was followed by an inductive descriptive analysis of the outputs. Our results demonstrate how meta-research can offer concrete contributions to address pressing challenges of TAI in healthcare. These challenges include the dynamic and complex nature of TAI ethical requirements and principles, common terminology and understanding of TAI, ensuring robustness, replicability, and reproducibility, choosing adequate evaluation metrics, lack of transparency, advancing preclinical biomedical research, and validation in real-world clinical environments. We present a catalog of ideas and a roadmap for future research, which synthesize existing interconnections and identify concrete next steps and open research gaps, thereby serving as a foundation for future interdisciplinary efforts.

Valerie Bürger, Marlie Besouw, Jana Fehr +26

QUEST Center for Responsible Research, Berlin Institute of Health (BIH) at Charité – Universitätsmedizin Berlin, Berlin, Germany · Department of Medical Imaging, Radboud University Medical Centre, Nijmegen, The Netherlands · Institute of Medical Informatics, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany +23

Responsible AI Trust in AI

Feb 24, 2026

"Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where compromised agents are weaponized against their human users. While extensive research focuses on agent-centric threats, human susceptibility to deception by a compromised agent remains unexplored. We present the first large-scale empirical study with 303 participants to measure human susceptibility to AMD. This is based on HAT-Lab (Human-Agent Trust Laboratory), a high-fidelity research platform we develop, featuring nine carefully crafted scenarios spanning everyday and professional domains (e.g., healthcare, software development, human resources). Our 10 key findings reveal significant vulnerabilities and provide future defense perspectives. Specifically, only 8.6% of participants perceive AMD attacks, while domain experts show increased susceptibility in certain scenarios. We identify six cognitive failure modes in users and find that their risk awareness often fails to translate to protective behavior. The defense analysis reveals that effective warnings should interrupt workflows with low verification costs. With experiential learning based on HAT-Lab, over 90% of users who perceive risks report increased caution against AMD. This work provides empirical evidence and a platform for human-centric agent security research.

Xinfeng Li, Shenyu Dai, Kelong Zheng +4

Nanyang Technological University · KTH · William & Mary

AI Agent Security Cybersecurity Trust in AI

Feb 24, 2026

What Drives Students' Use of AI Chatbots? Technology Acceptance in Conversational AI

Conversational AI tools have been rapidly adopted by students and are becoming part of their learning routines. This widespread use comes amid ongoing concerns about the reliability of AI-generated responses and the appropriate role of AI in education. Drawing on the Technology Acceptance Model, we examine how students' perceptions of conversational AI, including its usefulness, ease of use, trustworthiness, enjoyment, and social influence, relate to their intentions to use these tools for learning. We investigate both the direct and indirect relationships among these perceptions to understand how they are associated with students' behavioral intentions. Using survey data from 229 students and partial least squares structural equation modeling, we found that perceived usefulness was the strongest direct predictor of intention, followed by perceived enjoyment. Perceived ease of use, trust, and subjective norms did not have significant direct associations with intention. However, trust and subjective norms had significant total indirect associations, while perceived enjoyment had both significant direct and indirect associations. The model explained 70.2% of the variance in behavioral intention. These findings suggest that students' intentions to use conversational AI are associated less directly with effort-related considerations and more with perceived usefulness and affective experience. They also highlight the importance of understanding what students perceive as valuable in conversational AI interactions, particularly when designing tools intended to encourage engagement while supporting learning.

Griffin Pitts, Sanaz Motamedi

North Carolina State University, Raleigh, North Carolina, USA · Pennsylvania State University, University Park, Pennsylvania, USA

Conversational Agents Generative AI in Education Trust in AI

Feb 22, 2026

Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations

Experimental user studies evaluating the effectiveness of different subtypes of post-hoc explanations for black-box models are largely nonexistent. Therefore, the aim of this study was to investigate and evaluate how different types of counterfactual explanations, namely single point explanations and interval-based explanations, affect both model understanding and (demonstrated) trust. We conducted an online user study using a within-subjects experimental design, where the experimental arms were (i) no explanation (control), (ii) feature importance scores, (iii) point counterfactual explanations, and (iv) interval counterfactual explanations. Our results clearly show the superiority of interval explanations over other tested explanation types in increasing both model understanding and demonstrated trust in the AI. We could not support findings of some previous studies showing an effect of point counterfactual explanations compared to the control group. Our results further highlight the role individual differences in, for example, cognitive style or personality, in explanation effectiveness.

Tabea E. Röber, Paul Festor, Rob Goedhart +2

Amsterdam Business School, University of Amsterdam, The Netherlands · Department of Bioengineering, Imperial College London, UK · Institute of Artificial and Human Intelligence, University of Bayreuth, Germany

Counterfactual Explanations Explainability Evaluation Trust in AI

Feb 22, 2026

A User-driven Design Framework for Robotaxi

Robotaxis are emerging as a promising form of urban mobility, but removing human drivers fundamentally reshapes passenger-vehicle interaction and raises new design challenges. To inform robotaxi design based on real-world experience, we conducted 18 semi-structured interviews and autoethnographic ride experiences to examine users' perceptions, experiences, and expectations for robotaxi design. We found that users valued benefits such as increased agency and consistent driving. However, they also encountered challenges such as limited flexibility, insufficient transparency, and emergency handling concerns. Notably, users perceived robotaxis not merely as a mode of transportation, but as autonomous, semi-private transitional spaces, which made users feel less socially intrusive to engage in personal activities. Safety perceptions were polarized: some felt anxiety about reduced control, while others viewed robotaxis as safer than humans due to their cautious, law-abiding nature. Based on the findings, we propose a user-driven design framework spanning hailing, pick-up, traveling, and drop-off phases to support trustworthy, transparent, and accountable robotaxi design.

Yue Deng, Changyang He

Hong Kong University of Science and Technology, Hong Kong, China · Max Planck Institute for Security and Privacy, Bochum, Germany

Autonomous Driving Trust in AI Human-Robot Interaction

Feb 22, 2026

Defining Explainable AI for Requirements Analysis

Explainable Artificial Intelligence (XAI) has become popular in the last few years. The Artificial Intelligence (AI) community in general, and the Machine Learning (ML) community in particular, is coming to the realisation that in many applications, for AI to be trusted, it must not only demonstrate good performance in its decisionmaking, but it also must explain these decisions and convince us that it is making the decisions for the right reasons. However, different applications have different requirements on the information required of the underlying AI system in order to convince us that it is worthy of our trust. How do we define these requirements? In this paper, we present three dimensions for categorising the explanatory requirements of different applications. These are Source, Depth and Scope. We focus on the problem of matching up the explanatory requirements of different applications with the capabilities of underlying ML techniques to provide them. We deliberately avoid including aspects of explanation that are already well-covered by the existing literature and we focus our discussion on ML although the principles apply to AI more broadly.

Raymond Sheh, Isaac Monteath

(formerly) Department of Computing, Curtin University, Bentley WA 6102, Australia

Explainable Artificial Intelligence Trust in AI

Feb 20, 2026

Finding the Signal in the Noise: An Exploratory Study on Assessing the Effectiveness of AI and Accessibility Forums for Blind Users' Support Needs

Accessibility forums and, more recently, generative AI tools have become vital resources for blind users seeking solutions to computer-interaction issues and learning about new assistive technologies, screen reader features, tutorials, and software updates. Understanding user experiences with these resources is essential for identifying and addressing persistent support gaps. Towards this, we interviewed 14 blind users who regularly engage with forums and GenAI tools. Findings revealed that forums often overwhelm users with multiple overlapping topics, redundant or irrelevant content, and fragmented responses that must be mentally pieced together, increasing cognitive load. GenAI tools, while offering more direct assistance, introduce new barriers by producing unreliable answers, including overly verbose or fragmented guidance, fabricated information, and contradictory suggestions that fail to follow prompts, thereby heightening verification demands. Based on these insights, we outlined design opportunities to improve the reliability of assistive resources, aiming to provide blind users with more trustworthy and cognitively-manageable support.

Satwik Ram Kodandaram, Jiawei Zhou, Xiaojun Bi +2

Department of Computer Science, Stony Brook University, Stony Brook, New York, USA · Applied Math and Statistics, Stony Brook University, Stony Brook, New York, USA · Computer Science, Stony Brook University, Stony Brook, New York, USA +1

Human-AI Interaction Trust in AI

Feb 19, 2026

The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.

Uğur Genç, Heng Gu, Chadha Degachi +3

Delft University of Technology, Delft, Netherlands

Persuasion in Language Models Human-AI Decision Making Trust in AI

Jan 8, 2026

Large language models can effectively convince people to believe conspiracies

Large language models (LLMs) have been shown to be persuasive across a variety of contexts. But it remains unclear whether this persuasive power advantages accuracy, or if bad actors can just as easily use LLMs to promote misbeliefs. Here, we investigate this question across four experiments in which participants (N = 3996 Americans) discussed a conspiracy theory they were uncertain about with an LLM we instructed to either argue against ("debunking") or for ("bunking") that conspiracy. Across several frontier models (with standard guardrails but prompted to allow lying), we did not find consistent evidence of a truth advantage: the LLMs were able to both substantially increase and decrease average conspiracy belief, and participants in the bunking condition rated the LLM as more informative and collaborative, and reported greater trust in AI, than those who were in the debunking condition. More encouragingly, however, debunking induced more large changes in belief, and subsequent corrections were able to reverse the bunking effect. Furthermore, simply prompting the model to only provide accurate information dramatically reduced bunking effectiveness, and one powerful frontier model (GPT 5.2) almost entirely refused to promote conspiracies, suggesting that it is possible for the right guardrails to favor accurate beliefs. Finally, we did find a stark truth asymmetry in the context of information sharing: debunking had a large positive impact on mock social media posts composed by participants, while bunking had little effect. Overall, our findings show that people are not inherently less susceptible to AI that misleads than to AI that informs, but that potential technical solutions exist to mitigate this risk.

Thomas H. Costello, Kellin Pelrine, Matthew Kowal +6

Carnegie Mellon University · York University · Center for Research and Teaching in Economics +5

Deception in Language Models LLM Safety Persuasion in Language Models Trust in AI

Jan 6, 2026

The Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI

As conversational AI systems become a larger part of the media landscape, they raise questions about whose interests they serve and the risks they may pose to users. These systems do more than provide information: they increasingly offer advice and companionship through interfaces that can appear supportive and socially responsive. A pressing concern is that users may form perceived social relationships with these systems and place relational trust in them, even when the interests shaping interactions do not fully align with their own. The Fake Friend Dilemma (FFD) describes the problem that follows: the same relational trust that makes conversational AI useful can also leave users open to manipulation and exploitation when institutional interests conflict with their own. Drawing on work on relational trust, AI alignment, extractive design, and the political economy of communication, the paper considers how the FFD can manifest through product sales, propaganda and biased information, surveillance, and behavioral nudging. It also considers possible structural and technical mitigation strategies. The FFD is not simply about AI misleading users. The problem it surfaces is that the trust people place in these systems can itself become a resource for institutional actors seeking to influence behavior or extract information. The FFD is therefore as much a problem of media governance and political economy as it is a technological one.

Jacob Erickson

Vassar College, Poughkeepsie, NY, USA

Trust in AI AI Governance

Dec 12, 2025

CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?

Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach for trust prediction, owing to their ability to learn expressive node representations that capture intricate trust relationships within a network. However, current GNN-based trust prediction models face several limitations: (i) Most of them fail to capture trust dynamicity, leading to questionable inferences. (ii) They rarely consider the heterogeneous nature of real-world networks, resulting in a loss of rich semantics. (iii) None of them support context-awareness, a basic property of trust, making prediction results coarse-grained. To this end, we propose CAT, the first Context-Aware GNN-based Trust prediction model that supports trust dynamicity and accurately represents real-world heterogeneity. CAT consists of a graph construction layer, an embedding layer, a heterogeneous attention layer, and a prediction layer. It handles dynamic graphs using continuous-time representations and captures temporal information through a time encoding function. To model graph heterogeneity and leverage semantic information, CAT employs a dual attention mechanism that identifies the importance of different node types and nodes within each type. For context-awareness, we introduce a new notion of meta-paths to extract contextual features. By constructing context embeddings and integrating a context-aware aggregator, CAT can predict both context-aware trust and overall trust. Extensive experiments on three real-world datasets demonstrate that CAT outperforms five groups of baselines in trust prediction, while exhibiting strong scalability to large-scale graphs and robustness against both trust-oriented and GNN-oriented attacks.

Jie Wang, Zheng Yan, Jiahe Lan +2

State Key Laboratory of Integrated Services Networks, School of Cyber Engineering, Xidian University · Hangzhou Institute of Technology, Xidian University · Department of Computer Science, Purdue University

Temporal GNNs Heterogeneous GNNs Trust in AI

Nov 15, 2025

Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations

Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically perturbing reasoning chains and manipulating delivery tones. Specifically, we analyze reasoning errors in vision language models (VLMs) and how they impact user trust and the ability to detect errors. Our findings reveal two key effects: (1) users often equate trust with outcome agreement, sustaining reliance even when reasoning is flawed, and (2) the confident tone suppresses error detection while maintaining reliance, showing that delivery styles can override correctness. These results highlight how CoT explanations can simultaneously clarify and mislead, underscoring the need for NLP systems to provide explanations that encourage scrutiny and critical thinking rather than blind trust. All code will be released publicly.

Eunkyu Park, Wesley Hanwen Deng, Vasudha Varadarajan +4

Seoul National University · Human-Computer Interaction Institute, Carnegie Mellon University · Language Technologies Institute, Carnegie Mellon University

VLM Reasoning Multimodal CoT Reasoning Trust in AI Explainability Evaluation

Oct 30, 2025

Human-AI Complementarity: A Goal for Amplified Oversight

Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass human expert performance.

Rishub Jain, Sophie Bridgers, Lili Janzer +3

1Google DeepMind · 2Work done while previously at Google DeepMind

Human-AI Complementarity Claim Verification Trust in AI Human Oversight of AI