mlsanityData to 7 Oct 2026

Evaluating LLM Alignment With Human Trust Models

arXiv 2603.05839 ↗First posted 6 Mar 2026cs.MA cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 11 of its 23 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

11 of 23 references.

References · 11

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  4. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  5. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  6. 2023Steering Language Models With Activation Engineeringcited by 824
  7. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  8. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 303
  9. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 199
  10. 2024Norm Violation Detection in Multi-Agent Systems using Large Language Models: A Pilot Studycited by 6
  11. 2025Can LLMs Reason About Trust?: A Pilot Studycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A closer look at how large language models trust humans: patterns and biases
  2. 2025Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
  3. 2024Can Large Language Model Agents Simulate Human Trust Behavior?
  4. 2025Social preferences with unstable interactive reasoning: Large language models in economic trust games
  5. 2026Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs
  6. 2024Trusting Your AI Agent Emotionally and Cognitively: Development and Validation of a Semantic Differential Scale for AI Trust
  7. 2024More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
  8. 2025Computational Basis of LLM's Decision Making in Social Simulation