Lighthouse: A Trustworthy Digital Assistant for Exploring U.S. Civil Rights History Through Archives
arXiv:2610.30158 (cs.CL) | Submitted 24 September 2026
Authors: John A. Aydin, Angelica Williams, Steven Dindl, Nathan Saunders, Kate Boyd, Vandana Srivastava, Biplav Srivastava
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
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.
Key Contributions
- First-of-its-kind assistant: A digital assistant designed to help users explore the Civil Rights period of the United States, drawing on South Carolina archival data.
- Trustworthiness by design: Prioritizes the reliability of content and models/reduces potential harm to users from generated answers.
- Neuro-symbolic architecture: Combines LLM-based neural learning with rule-based symbolic reasoning, balancing answer risk against coverage breadth.
- Dual evaluation: Tests both objective factual questions (single acceptable answer) and subjective questions, using expert-aggregated "gold standard" QAs.
- Scalable corpus: Provides access to over 18k primary sources across multiple collections and is readily extensible.
Citation
Cite as: arXiv:2610.30158 [cs.CL]
DOI: https://doi.org/10.48550/arXiv.2610.30158
via ArXiv CL+LG