In my MA thesis, I built one example of how GraphRAG can work for historians. From 20,000 early modern documents, I constructed a knowledge graph of 218,000 entities and 692,000 relationships, then tested eight retrieval systems on thirty historical questions of escalating difficulty and then grading each of them. Plain RAG scored 48.4 percent against the metrics of groundedness, completeness, accuracy, synthesis, and usefulness. The best off-the-shelf system reached only 61.6 percent, an unacceptable result for a careful historian.
Part of the reason those systems created these kinds of errors was that they were not created for historical research. However, looking at these errors from a historian’s lens allowed me to create a better solution for history. Additionally, I noticed that those systems had a tendency to repress those entities which appear only rarely in the corpus. Sometimes, the most valuable entities, the obscure people and the once-mentioned places, are the very heart of where historical discovery is found. Fixing the systemic problems, and surfacing these obscure entities, were my goals in creating my own solution.
The outputs of many OCR technologies were developed for training LLMs, but that are frequently of little use in the humanities. They can be used by people with specific data mining and data science purposes, like researchers doing Named Entity Recognition. But these are still rather niche, and the majority of archival researchers and historians who want to access these OCR outputs would instead benefit from the document processing of OCR resulting in searchable archives. This is another area where AI-driven OCR is helpful, as it has the capacity to easily transform OCR outputs into specific and bespoke formats for the needs of the researchers who are using these outputs.
talkie’s poor representation of history is a side effect of a larger problem. The model was conceptually built as an experimental tool to see if language models can accurately predict the future, also known as “forecasting.” The blog post assertively claims the models predictive capabilities, yet is devoid of evidence enabling researchers to reproduce their experiment. The version that could serve serious research is gated behind compute, and is the same version released with no guardrails at all.
Dani K. Inkpen “History should make you feel weird.” So proclaims a widely touted slogan of history nerds. While there is much in the world foisting weirdness upon us today, too rarely do we intentionally seek the off-beat. History students should. “Weird,” though it has come to mean uncanny or bizarre, has its roots in the idea of the turning… Read more »
Daniyal Elahi and Harris Elahi In December 2025, ActiveHistory.ca published our first piece on Private Hasan Amat, a soldier of the 1st Battalion, Canadian Expeditionary Force, killed at the Battle of Hill 70 on August 20, 1917. To our knowledge, he is the first identified Muslim soldier killed in action serving with the CEF. He is also one of twenty-two… Read more »
We, at Active History, were saddened to learn about the passing of Danielle Terbenche. Her academic work and community involvement leaves a lasting impact. Danielle Terbenche completed her PhD at the University of Waterloo. During her time there, Danielle co-founded the Tri-University Graduate Students’ Association, published two peer-reviewed papers, and won the tri-university history programme’s award for “Best Paper or… Read more »
Kristen C. Howard In today’s increasingly online world, historians, researchers, and students want and expect online access to historical documents offered by galleries, libraries, archives, and museums. This includes not only journal articles and ebooks, but also primary sources and archival documents, which researchers increasingly expect to find online in searchable, digital formats. In turn, cultural heritage institutions have responded… Read more »
ActiveHistory.ca is on it’s summer hiatus, but we’ll be back with new content in mid-August. During the hiatus, we’re featuring some of our most popular and favourite posts from the past year. Thanks as always to our writers and readers.Originally published on January 21, 2026Meredith J. Batt I have made an error. These are not words that come easily to… Read more »
To date what has become painfully clear is that the responsibility and burden of truth telling has fallen largely on Indigenous Peoples, communities, and Nations. Survivors have been forced to continue to fight the church and state in court to have their records released and their experiences validated. We only have to consider the infamous St. Anne’s Residential School, where Survivors are in a legal battle for their records. According to Veldon Coburn, the continued failure of Indigenous and Northern Affairs[3] to release these illustrates,
There is no difference between the suppression of the truth and denial of the truth. Both tactics – whether deployed to advance reconciliation or resist it – subordinate Indigenous Peoples and their truth of Residential Schools and the integral part this system of cultural genocide played in colonialism.
