Metraipolis › archive › dc_72ca832c613f

LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation — arXiv:2609.33521

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33521
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:32.257Z
SHA-256 of the archived text
31218d463b10cd8e3db36f0db53cdf3817e65b022674f3095fbcbd49b04c5989
Stable URL of this page
https://metraipolis.com/documento/dc_72ca832c613f

How to cite

LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation — arXiv:2609.33521 — arXiv (en), https://arxiv.org/abs/2609.33521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72ca832c613f (Metraipolis archive dc_72ca832c613f, sha256 31218d463b10cd8e3db36f0db53cdf3817e65b022674f3095fbcbd49b04c5989)
BibTeX
@misc{dc72ca832c613f,
  title = {LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation — arXiv:2609.33521},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33521},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72ca832c613f; sha256 31218d463b10cd8e3db36f0db53cdf3817e65b022674f3095fbcbd49b04c5989},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Trust evaluation plays a critical role in cybersecurity by supporting risk mitigation and decision-making. A variety of trust evaluation methods have been proposed, with learning-based approaches offering high accuracy and automation. However, they often require substantial ground truth, suffer from low training efficiency, lack support for basic trust properties, and provide limited explainability. Large Language Models (LLMs) offer a compelling alternative due to their strong zero-/few-shot reasoning abilities and broad knowledge. To this end, we propose LLM4Trust, the first benchmark framework that systematically explores the capabilities of LLMs for trust evaluation. We first construct diverse trust graphs to model five basic trust properties and design corresponding property understanding tasks. We then assess the ability of eight representative LLMs to understand these properties under nine prompt methods. Based on this exploration, we identify the most effective LLM-prompt combinations and apply them to five real-world datasets for validating LLMs' trust evaluation capability. During this process, we propose two strategies to extract key information from large-scale trust graphs, addressing the context window limitations of LLMs. Extensive experiments show that LLMs can effectively understand basic trust properties and have great potential for real-world trust evaluation, particularly under limited supervision. However, they remain vulnerable to attacks targeting trust graphs and demonstration examples used in few-shot prompting, and incur high inference costs. Accordingly, we propose a defense mechanism and batch inference to improve the robustness and efficiency of LLM-based trust evaluation. The source code of LLM4Trust is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33521 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:27.973Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).