Current Large Language Models (LLMs), especially Large Reasoning Models, can generate Chain-of-Thought (CoT) reasoning traces to illustrate how they produce final outputs, thereby facilitating trust calibration for users. However, these CoT reasoning traces are usually lengthy and tedious, and can contain various issues, such as logical and factual errors, which make it difficult for users to interpret the reasoning traces efficiently and accurately. To address these challenges, we develop an error detection pipeline that combines external fact-checking with symbolic formal logical validation to identify errors at the step level. Building on this pipeline, we propose ReasonDiag, an interactive visualization system for diagnosing CoT reasoning traces. ReasonDiag provides 1) an integrated arc diagram to show reasoning-step distributions and error-propagation patterns, and 2) a hierarchical node-link diagram to visualize high-level reasoning flows and premise dependencies. We evaluate ReasonDiag through a technical evaluation for the error detection pipeline, two case studies, and user interviews with 16 participants. The results indicate that ReasonDiag helps users effectively understand CoT reasoning traces, identify erroneous steps, and determine their root causes.
Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors
强化学习技术成功地生成了令人信服的代理行为,但仍然很难定制行为以符合用户的特定偏好。在本文中,我们提出了一种新的交互方法,使用交互式解释,使用模板的自然语言作为一种通信方法。这种交互方法的主要优点是,它使用户和代理之间的双向通信通道;机器人可以解释其思维过程的用户,用户可以使用相同的交互式解释传达他们的行为偏好的机器人。通过这种方式,机器人的思维过程是透明的,用户可以向机器人提供纠正,包括建议采取的行动,要实现的目标以及这些决定背后的原因。我们在一个名为\textit{Super Mario Bros.}的视频游戏克隆中测试了我们提出的方法,结果表明我们的交互式解释方法在诊断和修复机器人行为方面是有效的。
DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors
The Hong Kong University of Science and Technology(香港科技大学);Tongji University(同济大学);Southeast University(东南大学);University of Waterloo(滑铁卢大学);ETH Zürich(苏黎世联邦理工学院)
InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems
East China Normal University(华东师范大学);Nanyang Technological University(南洋理工大学);Singapore Management University(新加坡管理大学);Hong Kong University of Science and Technology(香港科技大学)
SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
Zhejiang University(浙江大学);Binjiang Institute of Zhejiang University(浙江大学滨江研究院);The First Affiliated Hospital, Zhejiang University School of Medicine(浙江大学医学院附属第一医院);Shanghai Institute for Advanced Study of Zhejiang University(浙江大学上海高等研究院);Hunan University(湖南大学)
Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning
Research Center of Computational Life Science, Zhejiang Lab(浙江实验室计算生命科学研究中心);TransTek Medical(TransTek医疗);Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University(浙江大学医学院附属邵逸夫医院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
CoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through Comments
Sun Yat-sen University(中山大学);The Hong Kong University of Science and Technology(香港科技大学);College of Education, Zhejiang University(浙江大学教育学院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))