arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.16501cs.AI
收藏

通过视觉-语言模型引导人类决策者

Learning To Guide Human Decision Makers With Vision-Language Models

DI, University of Pisa(比萨大学DI);DISI, University of Trento(特伦托大学DISI);CIMEC, University of Trento(特伦托大学CIMEC);Rajib Pal Bankura Sammilani Medical College(拉吉布·帕尔班克尔医学学院)

Debodeep Banerjee, Stefano Teso, Burcu Sayin, Andrea Passerini

AI总结:

本文提出LTG框架,通过视觉-语言模型生成可解释的决策指导,使人类负责最终决策,提升高风险场景下的决策质量与可靠性。

摘要:

在高风险领域(如医疗诊断)中,AI系统支持人类决策以提高决策质量并减少认知负荷。主流方法将人类专家与机器学习模型结合,将低风险决策交由模型处理,使专家专注于需要判断的案例。然而,这种责任分离设置在高风险场景中并不足。专家可能因锚定偏差过度依赖机器决策,从而失去监管机构要求的可信AI监督。另一方面,专家在模型回避的(通常最困难的)决策上完全无帮助。为此,我们引入学习引导(LTG),一种替代框架,机器提供有助于决策的指导,而人类完全负责做出决策。为确保指导可解释且任务特定,我们开发SLOG,通过利用少量人类反馈,将任何视觉-语言模型转化为能够生成文本指导的有能力生成者。我们的实证评估展示了SLOG在合成数据集和具有挑战性的现实医疗诊断任务上的潜力。

英文摘要:

There is growing interest in AI systems that support human decision-making in high-stakes domains (e.g., medical diagnosis) to improve decision quality and reduce cognitive load. Mainstream approaches pair human experts with a machine-learning model, offloading low-risk decisions to the model so that experts can focus on cases that require their judgment. This separation of responsibilities setup, however, is inadequate for high-stakes scenarios. The expert may end up over-relying on the machine's decisions due to anchoring bias, thus losing the human oversight that is increasingly being required by regulatory agencies to ensure trustworthy AI. On the other hand, the expert is left entirely unassisted on the (typically hardest) decisions on which the model abstained. As a remedy, we introduce learning to guide (LTG), an alternative framework in which -- rather than taking control from the human expert -- the machine provides guidance useful for decision making, and the human is entirely responsible for coming up with a decision. In order to ensure guidance is interpretable and task-specific, we develop SLOG, an approach for turning any vision-language model into a capable generator of textual guidance by leveraging a modicum of human feedback. Our empirical evaluation highlights the promise of SLOG on both on a synthetic dataset and a challenging, real-world medical diagnosis task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑