arXiv cs.CL· John A. Aydin, Angelica Williams, Steven Dindl, Nathan Saunders, Kate Boyd, Vandana Srivastava, Biplav Srivastava·· 13 小时前AI 评分31
Lighthouse：面向民权运动档案的可信历史探索数字助手
Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives
AI 导读
研究者推出数字助手 Lighthouse，用于探索美国民权运动时期的历史档案，数据来自南卡罗来纳州。系统采用神经符号方法，将 LLM 的神经学习与基于规则的符号求解结合，以内容可信度和降低生成答案对用户的潜在伤害为设计原则。Lighthouse 可访问超过 18k 份一手资料，并同时用事实性客观问题与主观问题（由独立专家答案聚合出"金标准"）进行评估。
正文 · 原文
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. 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. 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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.30158 [cs.CL] |
| (or arXiv:2610.30158v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30158 arXiv-issued DOI via DataCite |
Submission history
From: John Aydin [view email]
[v1]
Thu, 24 Sep 2026 02:22:04 UTC (2,743 KB)
来源：arXiv cs.CL · arxiv.org