Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives

查看原文 / View Original 编辑 / Edit

Computer Science > Computation and Language arXiv:2610.30158 (cs) [Submitted on 24 Sep 2026] Title: Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives Authors: John A. Aydin, Angelica Williams, Steven Dindl, Nathan Saunders, Kate Boyd, Vandana Srivastava, Biplav Srivastava.

计算机科学 > 计算与语言 arXiv:2610.30158 (cs) [提交于 2026 年 9 月 24 日] 标题：灯塔：构建用于探索民权档案历史的可信数字助理作者：John A. Aydin, Angelica Williams, Steven Dindl, Nathan Saunders, Kate Boyd, Vandana Srivastava, Biplav Srivastava。

Abstract: Artificial intelligence (AI), as a decision-support aid, provides new tools for studying history effectively using multimodal data, including text, images, and audio. We present, to our knowledge, the first digital assistant named Lighthouse—commonly called a chatbot—for exploring the Civil Rights period of the United States using data from South Carolina.

摘要：人工智能（AI）作为一种决策支持辅助工具，为利用包括文本、图像和音频在内的多模态数据有效研究历史提供了新工具。据我们所知，我们提出了第一个名为“灯塔”（Lighthouse）的数字助理——通常被称为聊天机器人——用于利用南卡罗来纳州的数据探索美国的民权时期。

From an AI perspective, the system’s novelty lies in its guiding design principles of (a) focusing on trustworthiness of content and (b) by modeling and reducing potential harm to users from generated answers. It implements these with a neuro-symbolic approach that combines neural learning through a large language model (LLM) with rule-based symbolic solving, balancing risk of answers with generality of coverage.

从人工智能的角度来看，该系统的创新之处在于其指导设计原则：（a）关注内容的可信度，以及（b）通过建模和减少生成答案对用户造成的潜在伤害。它通过一种神经符号方法实现了这些原则，该方法将通过大型语言模型（LLM）进行的神经学习与基于规则的符号求解相结合，在答案的风险与覆盖的广度之间取得平衡。

We evaluate Lighthouse with both factual objective questions that admit a single acceptable answer as well as subjective questions. For the latter, a dataset of subjective question-answer pairs (QAs) is created by discovering a “gold standard” by aggregating answers from independent experts. Lighthouse has access to over 18k primary sources from a range of collections and can be easily extended.

我们通过承认单一可接受答案的事实性客观问题以及主观问题来评估“灯塔”。对于后者，通过汇总独立专家的答案来发现“黄金标准”，从而创建了一个主观问答对（QA）数据集。“灯塔”可以访问来自多个馆藏的超过 1.8 万份原始资料，并且可以轻松扩展。