Computational retrieval finds biblical echoes in Blixen’s tales, with mixed gains
A study evaluates AI’s ability to spot Bible references in Karen Blixen’s Seven Gothic Tales.
- Publication
- arXiv
- Stage
- Preprint
- What we read
- Summary of the paper
- Authors
- András Kovács, Alexander Conroy, Daniel Hershcovich, Jens Bjerring-Hansen
- Universities and research institutions
- Not yet supplied in verified metadata; the Brief does not guess.
What they did and found
Researchers tested lexical and dense models against 189 annotated references across 31,170 Bible verses. They found strong baseline lexical retrieval and notable gains after task-specific tuning, but many expert-annotated matches remained non-obvious.
Why it matters
Shows practical limits when using AI to surface literary parallels; tuning helps find less explicit ties, but human judgment stays essential.
The study compared simple word-based methods with context-aware encoders and found lexical search remains strong for exact quotes, while targeted tuning helped identify paraphrases and allusions.
In practice, a team could use AI to propose candidate passages for close reading, but must review how translations and scholarly aims shape relevance.
Original sources · 1
- Retrieving Biblical Intertextual References in Karen Blixen's Seven Gothic Tales ↗arXiv · 2026-09-28
Check the original paper for its authors, methods, version and access terms.
What remains uncertain
Ground truth is selective; not every plausible reference is recorded and results depend on translation choices.
What is your take?
Ask a question, add useful context or share a different perspective. Keep the conversation respectful and grounded.