Althea：面向事实核查和批判性推理的人机协作
Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
AI总结：
Althea通过整合问题生成、证据检索和结构化推理，提升在线主张的核查效率与准确性，其在AVeriteC基准测试中达到宏F1值0.44，且在用户研究中显示指导性交互对短期准确性和长期改进均有显著影响。
摘要：
网络信息生态系统需要可扩展且知识上可信的事实核查系统。自动化方法效率高但缺乏透明性，而人工验证则效率低且不一致。我们引入Althea，一种检索增强型系统，整合问题生成、证据检索和结构化推理，以支持用户驱动的在线主张评估。在AVeriteC基准测试中，Althea达到宏F1值0.44，优于标准验证流程，并能更好地区分支持和反驳的主张。我们进一步通过受控用户研究和纵向调查实验（N=963）评估Althea，比较三种交互模式：探索模式提供引导推理，总结模式提供综合结论，自我搜索模式提供程序指导而不干预算法。结果表明，引导交互在短期准确性及信心上提升最强，而自我搜索在长期改进上更显著。这种模式表明，性能提升不仅由努力或暴露驱动，而是由认知工作结构和内部化决定。参与者一致认为Althea透明且支持反思性推理，强调其组织证据和澄清竞争性主张的能力。通过整合检索、交互和教学支架，Althea展示了人机交互如何超越自动化裁决，向持续改进推理迈进。这些发现推动了设计可信、以人类为中心的事实核查系统，平衡指导与知识自主性。
英文摘要：
Fact-checking systems must be scalable and epistemically trustworthy. We introduce Althea, a retrieval-augmented system for user-driven claim evaluation that matches standard pipelines on AVeriTeC while improving supported/refuted discrimination. A longitudinal survey experiment (N=961) treats a ten-day follow-up as a fading test: after modeling a verification procedure, we remove the system and ask whether users reproduce it unaided, testing metalearning rather than one-time accuracy. We compare two AI-assisted treatments, Exploratory (guided reasoning) and Summary (synthesized verdicts), against two baselines, unrelated news and Self-search. The treatments yield the strongest immediate accuracy and confidence gains but do not survive the fading test: on unseen claims they perform no better than news, while Self-search, with no procedure to fade, retains a large advantage. This reveals a factchecking-metalearning tradeoff: conditions that most improve immediate accuracy are least likely to produce metalearning, cautioning against treating AI-delivered verdicts as a source of durable literacy gains.
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。
