Lighthouse chatbot to our knowledge launched for Civil Rights history research
Lighthouse is a new digital assistant that lets users explore the Civil Rights period of the United States using multimodal data from South Carolina. The authors present it as the first system of its kind.
Key points
- Lighthouse chatbot, first digital assistant for Civil Rights history, uses multimodal data from South Carolina
- Combines a large language model with rule‑based symbolic solving in a neuro‑symbolic framework to reduce risk and improve trustworthiness
- Evaluated on factual and subjective questions; dataset of subjective QAs built from independent experts; accesses over 18k primary sources
The assistant uses a neuro‑symbolic design that blends a large language model with rule‑based symbolic solving, aiming to reduce potential harm while maintaining coverage. Evaluation involved both factual objective questions and subjective ones, with a dataset of subjective question‑answer pairs built by aggregating answers from independent experts.
Lighthouse can access over 18k primary sources from a variety of collections and is designed to be easily extended. The work highlights how AI can support historical research while prioritizing trustworthiness and safety.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- MIT historian says early AI engineers added randomness to mimic human creativity · 1 src
- Researchers introduce MemPlan for text-based planning with PDDL · 1 src
- Researchers present CiteAnchor framework for detecting hallucinated citations · 1 src
- Researchers find self‑rewarded moral argumentation makes language models decisive but pliable · 1 src
- AQL-Lite improves Arabic LLMs with curated data and partial-parameter training · 1 src
Comments
via GitHub Discussions