TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning

TL;DR

TRUST introduces a decentralized, transparent framework for auditing large language models' reasoning processes, enhancing scalability, robustness, and privacy while ensuring accountability and detecting flaws across diverse tasks.

Contribution

It presents a novel decentralized auditing framework with blockchain-based transparency, consensus among diverse auditors, and privacy-preserving reasoning segmentation, addressing key limitations of centralized methods.

Findings

Effectively detects reasoning flaws in multiple LLMs.

Maintains robustness against adversarial auditors.

Scales to complex reasoning tasks with hierarchical DAG decomposition.

Abstract

Large Language Models generate complex reasoning chains that reveal their decision-making, yet verifying the faithfulness and harmlessness of these intermediate steps remains a critical unsolved problem. Existing auditing methods are centralized, opaque, and hard to scale, creating significant risks for deploying proprietary models in high-stakes domains. We identify four core challenges: (1) Robustness: Centralized auditors are single points of failure, prone to bias or attacks. (2) Scalability: Reasoning traces are too long for manual verification. (3) Opacity: Closed auditing undermines public trust. (4) Privacy: Exposing full reasoning risks model theft or distillation. We propose TRUST, a transparent, decentralized auditing framework that overcomes these limitations via: (1) A consensus mechanism among diverse auditors, guaranteeing correctness under up to $30\%$ malicious participants. (2) A hierarchical DAG decomposition of reasoning traces, enabling scalable, parallel auditing. (3) A blockchain ledger that records all verification decisions for public accountability. (4) Privacy-preserving segmentation, sharing only partial reasoning steps to protect proprietary logic. We provide theoretical guarantees for the security and economic incentives of the TRUST framework. Experiments across multiple LLMs (GPT-OSS, DeepSeek-r1, Qwen) and reasoning tasks (math, medical, science, humanities) show TRUST effectively detects reasoning flaws and remains robust against adversarial auditors. Our work pioneers decentralized AI auditing, offering a practical path toward safe and trustworthy LLM deployment.