We present a two-stage system for the SemEval Narrative Similarity task that separates representation learning from comparative decision making. In Track B, we adapt a frozen large-scale embedding model using a lightweight projection layer trained with a triplet objective and hard example mining, producing a task-specific similarity space. In Track A, similarity scores derived from the adapted embedding space are incorporated into a large language model, which performs the final binary decision. On the official test set, our system achieves 0.68 accuracy on Track A and 0.66 on Track B, clearly outperforming the provided baselines and ranking 20th out of 44 teams on Track A and 10th out of 27 teams on Track B. These results demonstrate that efficient embedding adaptation combined with embedding-informed LLM reasoning is effective for modeling high-level narrative similarity.

While digitized corpora have transformed the study of intellectual transmission, current methods rely heavily on lexical text reuse detection, capturing verbatim quotations but fundamentally missing paraphrases and complex implicit engagement. This paper evaluates semantic search in 18th-century intellectual history through the reception of John Locke’s foundational work. Using expert annotation grounded in a semantic taxonomy, we examine whether an off-the-shelf semantic search pipeline can surface meaning-level correspondences overlooked by lexical methods. Our results demonstrate that semantic search retrieves substantially more implicit receptions than lexical baselines. However, linguistic diagnostics also reveal a “lexical gatekeeping” effect, where retrieval remains partially constrained by surface vocabulary overlap. These findings highlight both the potential and the limitations of semantic retrieval for analyzing the circulation of ideas in large historical corpora. The data is available at https://github.com/COMHIS/locke-sim-data.

This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts. We benchmark and evaluate the performance of large foundation models against a multimodal dataset of 724 annotated pages. The results demonstrate that reliable Latin detection with contemporary zero-shot models is achievable, yet these models lack a functional comprehension of Latin. This study establishes a comprehensive baseline for processing Latin within mixed-language corpora, supporting quantitative analysis in intellectual history and historical linguistics. Both the dataset and code are available at https://github.com/COMHIS/EACL26-detect-latin.

This short paper studies the distribution of Scotticisms from a list compiled by David Hume in a large collection of 18th century publications. We use regular expression search to find the items on the list in the ECCO collection, and then apply regression analysis to test whether the distribution of Scotticisms in works first published in Scotland is significantly different from the distribution of Scotticisms in works first published in England. We further refine our analysis to trace the influence of variables such as publication date, genre and author’s country of origin.

In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents. The ECCO dataset poses unique modelling challenges due to the presence of Optical Character Recognition (OCR) artifacts. We establish the performance of the BERT model on a publication year prediction task against linear baseline models and human judgement, finding the BERT model to be superior to both and able to date the works, on average, with less than 7 years absolute error. We also explore how language change over time affects the model by analyzing the features the model uses for publication year predictions as given by the Integrated Gradients model explanation method.