Evaluating LLM Alignment With Human Trust Models

• URL: http://arxiv.org/abs/2603.05839v1
• Date: Fri, 06 Mar 2026 02:49:49 GMT
• Title: Evaluating LLM Alignment With Human Trust Models
• Abstract summary: This work presents a white-box analysis of trust representation in EleutherAI/gpt-j-6B.<n>We first identified trust-related concepts from five established human trust models.<n>We then measured the cosine similarities between the LLM's internal representation of trust and the derived trust-related concepts.
• Score: 9.741889240149336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ONTrust: A Reference Ontology of Trust [1.068745732421904]
  This paper is the culmination of a long-term research program of providing a solid ontological foundation on trust.<n>A Reference Ontology of Trust (ONTrust) was developed, grounded on the Unified Foundational Ontology and specified in OntoUML.<n>ONTrust formally characterizes the concept of trust and its different types, describes the different factors that can influence trust, as well as explains how risk emerges from trust relations.
  arXiv  Detail & Related papers  (2026-02-07T18:47:34Z)
• Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems [94.9141394384021]
  Individual agents in multi-agent systems often lack robustness, tending to blindly conform to misleading peers.<n>We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability.<n>We first formalize the learning problem of history-aware reference, introducing the historical interactions of peers as additional input.<n>We then develop Epistemic Context Learning (ECL), a reasoning framework that conditions predictions on explicitly-built peer profiles from history.
  arXiv  Detail & Related papers  (2026-01-29T13:59:32Z)
• UniCog: Uncovering Cognitive Abilities of LLMs through Latent Mind Space Analysis [69.50752734049985]
  A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans.<n>We propose UniCog, a unified framework that analyzes LLM cognition via a latent mind space.
  arXiv  Detail & Related papers  (2026-01-25T16:19:00Z)
• Revisiting Trust in the Era of Generative AI: Factorial Structure and Latent Profiles [5.109743403025609]
  Trust is one of the most important factors shaping whether and how people adopt and rely on artificial intelligence (AI)<n>Most existing studies measure trust in terms of functionality, focusing on whether a system is reliable, accurate, or easy to use.<n>In this study, we introduce and validate the Human-AI Trust Scale (HAITS), a new measure designed to capture both the rational and relational aspects of trust in GenAI.
  arXiv  Detail & Related papers  (2025-10-11T12:39:53Z)
• Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness [4.008152563028669]
  Large language models (LLMs) have emerged as powerful tools for simulating complex social phenomena using human-like agents.<n>This study investigates the influence of value similarity on relationship-building among LLM agents through two experiments.
  arXiv  Detail & Related papers  (2025-07-16T07:21:59Z)
• Ties of Trust: a bowtie model to uncover trustor-trustee relationships in LLMs [1.1149261035759372]
  We introduce a bowtie model for conceptualizing and formulating trust in Large Language Models (LLMs)<n>A core component comprehensively explores trust by tying its two sides, namely the trustor and the trustee, as well as their intricate relationships.<n>We uncover these relationships within the proposed bowtie model and beyond to its sociotechnical ecosystem.
  arXiv  Detail & Related papers  (2025-06-11T11:42:52Z)
• A closer look at how large language models trust humans: patterns and biases [0.0]
  Large language models (LLMs) and LLM-based agents increasingly interact with humans in decision-making contexts.<n>LLMs rely on some sort of implicit effective trust in trust-related contexts to assist and affect decision making.<n>We study whether LLMs trust depends on the three major trustworthiness dimensions: competence, benevolence and integrity of the human subject.<n>We find that in most, but not all cases, LLM trust is strongly predicted by trustworthiness, and in some cases also biased by age, religion and gender.
  arXiv  Detail & Related papers  (2025-04-22T11:31:50Z)
• Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents [61.132523071109354]
  This paper investigates the interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios.<n>Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" stances than pure game-theoretic agents.
  arXiv  Detail & Related papers  (2025-04-11T15:41:21Z)
• Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations [48.07182711678573]
  ASTrust generates explanations grounded in the relationship between model confidence and syntactic structures of programming languages. We develop an automated visualization that illustrates the aggregated model confidence scores superimposed on sequence, heat-map, and graph-based visuals of syntactic structures from ASTs.
  arXiv  Detail & Related papers  (2024-07-12T04:38:28Z)
• TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support [59.41529066449414]
  We propose TrustGuard, a GNN-based accurate trust evaluation model that supports trust dynamicity. TrustGuard is designed with a layered architecture that contains a snapshot input layer, a spatial aggregation layer, a temporal aggregation layer, and a prediction layer. Experiments show that TrustGuard outperforms state-of-the-art GNN-based trust evaluation models with respect to trust prediction across single-timeslot and multi-timeslot.
  arXiv  Detail & Related papers  (2023-06-23T07:39:12Z)
• Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI [55.4046755826066]
  We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i.e., trust between people) We incorporate a formalization of 'contractual trust', such that trust between a user and an AI is trust that some implicit or explicit contract will hold. We discuss how to design trustworthy AI, how to evaluate whether trust has manifested, and whether it is warranted.
  arXiv  Detail & Related papers  (2020-10-15T03:07:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.