Control hallucinations. Ground your research in concrete sources.
BookWyrm provides researchers with tools to extract, cite, and structure information from large document collections, ensuring every AI-generated claim is backed by verifiable evidence. Works seamlessly with PDF extraction for research papers.
{
"query": "climate change impacts on agriculture",
"pdf_path": "research_paper.pdf",
"total_citations": 12,
"citations": [
{
"text": "Climate change has significantly reduced corn yields in the Midwest...",
"reasoning": "This directly addresses agricultural impacts of climate change",
"quality": 4,
"llm_score": 5,
"llm_explanation": "5 - Comprehensive account that fully addresses the query",
"start_page": 15,
"end_page": 15
}
],...
}In research, AI can process more information than any human.
But without clear citations, the output can't be trusted.
Most LLM pipelines summarize or paraphrase text without linking back to the original source, leading to hallucinations and unverifiable claims, unacceptable in academic contexts.
Researchers need systems that accelerate reading and referencing, not ones that add another layer of verification work.
BookWyrm's cite endpoint was designed for “citation under question”, a process where an AI reads a document deeply with a specific research query in mind, surfacing only direct excerpts with position data.
Instead of inventing text, the model retrieves and ranks real passages from the source, allowing researchers to trace every claim back to its origin.
The response includes:
This allows you to verify and filter supporting evidence before passing it to research assistants or domain experts.
# Analyze a document for climate change impacts
uv run citation-workflow research_paper.pdf query_climate.txt --output results.json
Describe any mentions of climate change impacts on agriculture, including changes in crop yields, farming practices, or agricultural adaptation strategies.{
"query": "climate change impacts on agriculture",
"pdf_path": "research_paper.pdf",
"total_citations": 12,
"citations": [
{
"text": "Climate change has significantly reduced corn yields in the Midwest...",
"reasoning": "This directly addresses agricultural impacts of climate change",
"quality": 4,
"llm_score": 5,
"llm_explanation": "5 - Comprehensive account that fully addresses the query",
"start_page": 15,
"end_page": 15
}
],...
}When working with Dr. Peter Turchin and the Complexity Science Hub in Vienna, the challenge was verifying AI-identified historical events from long, complex documents, often 400+ pages.
Their pipeline used AI to suggest potential events but relied entirely on human review for validation.
BookWyrm's citation process is able to automate the “deep read” step:
The entire pipeline reduced multi-hour verification work to a few minutes, with the AI producing reviewable, source-backed evidence.
📕 Read More: AI Driven Citation: Controlling Hallucinations With Concrete Sources and Citation with Big Context Models.
Using BookWyrm's API, you can:
This architecture supports multi-model setups where lightweight LLMs perform the initial scan and more powerful ones perform semantic validation, all grounded by BookWyrm's position-aware extraction.
No hallucinated text: Each citation refers to an actual position in a real document.
Fast processing: Smaller LLMs can traverse hundreds of pages in minutes.
Composable: The workflow is modular and can plug into existing research pipelines.
Recoverable: Long document processing can be resumed if interrupted.
BookWyrm transforms hundreds of pages into reviewable evidence, cutting manual reading time and reducing verification load.
Join the beta and start building AI-driven research tools that cite their sources.