Multi-View Trust Evaluation for Collaborator Selection via Evidential Deep Learning

• URL: http://arxiv.org/abs/2608.25235v1
• Date: Tue, 25 Aug 2026 23:52:26 GMT
• Title: Multi-View Trust Evaluation for Collaborator Selection via Evidential Deep Learning
• Abstract summary: We propose a novel multi-view evidential learning (MVE) based trust evaluation method.<n>First, we model each task owner who has interacted with a potential collaborator as an independent observational view.<n>Second, to address the dynamic evolution of trust under changing conditions, we leverage the powerful long-sequence modeling capability of the Mamba model.<n>Third, to quantify the certainty levels of view-specific trust assessments, we incorporate an evidential deep learning mechanism in MVE.
• Score: 11.560090481333622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Selection of trustworthy collaborators in distributed systems is critical for efficient task completion, necessitating the inference of trustworthiness from their past collaboration experience. However, as a collaborator serves distinct devices across diverse scenarios in past collaborations, its trust-related data, observed from different device-specific views, is inherently multi-source, heterogeneous, and uneven in quality. Consequently, achieving accurate trust evaluations for collaborator selection remains a major challenge. To tackle these issues, we propose a novel multi-view evidential learning (MVE) based trust evaluation method. First, to accommodate the multi-source heterogeneity of observed trust-related data, we model each task owner who has interacted with a potential collaborator as an independent observational view, enabling the evaluation of the collaborator's view-specific trust. Second, to address the dynamic evolution of trust under changing conditions, we leverage the powerful long-sequence modeling capability of the Mamba model to capture the deep temporal patterns of a collaborator's trust state within each view. Furthermore, to quantify the certainty levels of view-specific trust assessments, we incorporate an evidential deep learning mechanism in MVE, which outputs trust evaluation results while quantifying the subjective uncertainty underlying them. Finally, we employ a dynamic evidential fusion strategy to adaptively integrate the multi-view evidence based on their respective quantified uncertainties, thereby yielding a final trust evaluation for the collaborator. Extensive experiments demonstrate that the proposed MVE method outperforms baselines in both trust evaluation accuracy and task success rate.

Related papers

• TrustFormer: Cross-Temporal and Cross- Dimensional Transformer for Task-Specific Multi-Dimensional Trust Evaluation [11.560090481333622]
  TrustFormer is a task-specific multi-dimensional trust evaluation framework.<n>It learns the multi-dimensional trust evolution of potential collaborators from historical performance data.<n>It yields a 40.8% improvement in trust evaluation accuracy and enabling more reliable collaborator selection.
  arXiv  Detail & Related papers  (2026-08-25T23:57:18Z)
• Confidence Estimation for LLMs in Multi-turn Interactions [48.081802290688394]
  This work presents the first systematic study of confidence estimation in multi-turn interactions.<n>We establish a formal evaluation framework grounded in two key desideratas: per-turn calibration and monotonicity of confidence.<n>Our work provides a foundational methodology for developing more reliable and trustworthy conversational agents.
  arXiv  Detail & Related papers  (2026-01-05T14:58:04Z)
• BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents [58.05949210993854]
  We investigate whether search agents have the ability to communicate their own confidence through verbalized confidence scores after long sequences of actions.<n>We propose Test-Time Scaling (TTS) methods that use confidence scores to determine answer quality, encourage the model to try again until reaching a satisfactory confidence level.
  arXiv  Detail & Related papers  (2025-10-27T15:58:51Z)
• Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI [51.4138877170325]
  We propose a task-specific trust semantics distillation model based on a large AI model (LAM)-driven teacher-student agent architecture.<n>The proposed 2TSD model can reduce collaborator evaluation time, decrease device resource consumption, and improve the accuracy of collaborator selection.
  arXiv  Detail & Related papers  (2025-09-09T21:18:31Z)
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation [63.49409574310576]
  Large language models (LLMs) exhibit overconfidence, assigning high confidence scores to incorrect predictions.<n>We introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation.<n>Our code and all baselines used in the paper are available on GitHub.
  arXiv  Detail & Related papers  (2025-08-16T13:29:35Z)
• Semantic Chain-of-Trust: Autonomous Trust Orchestration for Collaborator Selection via Hypergraph-Aided Agentic AI [57.58120823855315]
  This paper proposes an autonomous trust orchestration method based on a new concept of semantic chain-of-trust.<n>Our technique employs agentic AI and hypergraph to establish and maintain trust relationships among devices.<n> Experimental results demonstrate that the proposed method achieves resource-efficient trust evaluation.
  arXiv  Detail & Related papers  (2025-07-31T13:53:25Z)
• Chain-of-Trust: A Progressive Trust Evaluation Framework Enabled by Generative AI [20.02079841777494]
  Chain-of-trust framework is proposed to make better use of device attribute data.<n>The framework divides the trust evaluation process into chained stages based on task decomposition.<n>generative AI is employed to analyze and interpret the collected data to produce correct evaluation results.
  arXiv  Detail & Related papers  (2025-06-20T16:33:03Z)
• Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models [14.5291643644017]
  We introduce the concept of Confidence-Probability Alignment. We probe the alignment between models' internal and expressed confidence. Among the models analyzed, OpenAI's GPT-4 showed the strongest confidence-probability alignment.
  arXiv  Detail & Related papers  (2024-05-25T15:42:04Z)
• Improving the Reliability for Confidence Estimation [16.952133489480776]
  Confidence estimation is a task that aims to evaluate the trustworthiness of the model's prediction output during deployment. Previous works have outlined two important qualities that a reliable confidence estimation model should possess. We propose a meta-learning framework that can simultaneously improve upon both qualities in a confidence estimation model.
  arXiv  Detail & Related papers  (2022-10-13T06:34:23Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)

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.