用去中心化技术+人机协作，让大模型在关键决策中更安全可追溯。
Responsible LLM Deployment for High-Stake Decisions by Decentralized Technologies and Human-AI Interactions
- 通过人机多轮交互评估模型不确定样本与解释稳定性。
- 本地部署结合区块链/IPFS，实现决策记录不可篡改审计。
- 在金融信贷场景验证，适配Bert、Mistral、LLaMA系列模型。
高风险决策领域正探索大型语言模型（LLMs）在复杂决策中的应用。然而，真实场景中部署LLM面临数据安全、脱离受控环境后能力评估困难、以及恶意决策责任归属不清等挑战。本文提出一种通过主动引入人类参与的负责任部署框架：在部署前通过开发者与专家的多轮互动，评估模型对不确定样本的处理能力，并判断事后可解释性（XAI）技术生成解释的稳定性。同时，建议在组织内部本地部署LLM，并结合区块链与IPFS等去中心化技术，创建不可篡改的模型活动记录，支持自动化审计以提升安全性并实现责任可追溯。该方法在Bert-large-uncased、Mistral、LLaMA 2 和 LLaMA 3 模型上进行了测试，评估其在企业贷款等金融决策场景中支持负责任决策的能力。
原文摘要 · Abstract (English)
High-stakes decision domains are increasingly exploring the potential of Large Language Models (LLMs) for complex decision-making tasks. However, LLM deployment in real-world settings presents challenges in data security, evaluation of its capabilities outside controlled environments, and accountability attribution in the event of adversarial decisions. This paper proposes a framework for responsible deployment of LLM-based decision-support systems through active human involvement. It integrates interactive collaboration between human experts and developers through multiple iterations at the pre-deployment stage to assess the uncertain samples and judge the stability of the explanation provided by post-hoc XAI techniques. Local LLM deployment within organizations and decentralized technologies, such as Blockchain and IPFS, are proposed to create immutable records of LLM activities for automated auditing to enhance security and trace back accountability. It was tested on Bert-large-uncased, Mistral, and LLaMA 2 and 3 models to assess the capability to support responsible financial decisions on business lending.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。