aiqbench analysis
This arXiv paper applies neural language model embeddings to mythological and religious texts, building an interactive tool for finding cross-cultural semantic parallels. Its most useful finding for AI readers is the caveat: the authors test how much of the embedding geometry lexical overlap and proper names already explain, which is a useful check on whether such models capture meaning or surface features. Readers interested in embedding evaluation for humanities corpora should weigh that analysis more than the tool itself.
MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions
arXiv:2610.28452v1 Announce Type: new Abstract: We present a tool for the comparative study of mythological and religious texts. Traditional manual analysis is highly labor-intensive and difficult to scale. To address this, we use neural language models to embed texts into a shared semantic space, so that users can find semantic parallels across cultural traditions in an interactive interface. Embedded fragments form distinct semantic structures whose coarse geometry aligns with well-documented historical relations between traditions. We quantify how much of that geometry is already explained by lexical overlap and by proper names. The current system is available at https://mythoscope.io, and the installable package is available at https://github.com/haafus/MythoSemantic/blob/main/RUN.md.
Abstract:We present a tool for the comparative study of mythological and religious texts. Traditional manual analysis is highly labor-intensive and difficult to scale. To address this, we use neural language models to embed texts into a shared semantic space, so that users can find semantic parallels across cultural traditions in an interactive interface. Embedded fragments form distinct semantic structures whose coarse geometry aligns with well-documented historical relations between traditions. We quantify how much of that geometry is already explained by lexical overlap and by proper names. The current system is available at this https URL, and the installable package is available at this https URL.
Computation and Language (cs.CL)
I.2.7; H.3.3; J.5
arXiv:2610.28452 [cs.CL]
(or arXiv:2610.28452v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.28452 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 203 words