InSight：交互式可视化中智能体主张验证的基准
InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations
浏览论文内容
中文总结 AI 辅助
本文提出InSight基准，用于交互式可视化中的智能体主张验证，含21349条主张，评估显示交互式验证仍是重大挑战，相关资源已发布。
中文摘要 AI 辅助
视觉语言模型在解释静态视觉作品方面表现出卓越能力，但现代数据分析本质上是动态的，需要对交互式环境进行主动探查。现有基准大多局限于静态图像和单次问答，无法捕捉该领域的认知需求，在该领域中，证据常被遮挡、分布在关联视图中，或通过用户智能体有条件地呈现。本文提出InSight，一个针对交互式可视化的智能体主张验证基准。该数据集包含21349条主张，源自人类撰写的分析叙述，并基于完全交互式的基于网页的环境。智能体必须在这些环境中导航，以确定给定可用证据下，自然语言主张是否得到支持、被反驳或无法验证。与传统评估不同，InSight将交互轨迹视为推理的内在代理，从而能够严格审查模型如何寻找和综合视觉证据。我们对最先进的模型进行评估，发现交互式验证仍然是一项重大挑战。我们在该httpsURL发布InSight。
英文摘要
Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture the epistemic demands of this domain, where evidence is frequently occluded, distributed across linked views, or conditionally revealed through user agency. In this paper, we introduce InSight, a benchmark for agentic claim verification over interactive visualizations. The dataset consists of 21,349 claims derived from human-authored analytical narratives and grounded in fully interactive web-based environments. Agents must navigate these environments to determine whether a natural language claim is supported, refuted or not verifiable given the available evidence. Unlike traditional evaluations, InSight treats interaction traces as intrinsic proxies for reasoning, enabling a rigorous audit of how models seek and synthesize visual evidence. We evaluate state-of-the-art models, revealing that interactive verification remains a non-trivial challenge. We release InSight at https://github.com/maevehutch/insight.
发表机构
- City, University of London（伦敦城市大学）
- Imperial College London（帝国理工学院）
- The Alan Turing Institute（艾伦·图灵研究所）
机构由 AI 辅助整理，请以论文原文为准。
