aiqbench analysis
Inspicio demonstrates a significant advancement in handling historical and low-resource languages by leveraging instruction-tuned LLMs to bridge tokens directly to the Open English WordNet without needing pre-existing source-language inventories. This approach effectively solves word sense disambiguation for ancient texts like Latin and Ancient Greek, achieving high recall through a hybrid retrieval strategy that combines dense similarity with sparse lemma matching. The research highlights how modern generative models can democratize NLP capabilities for linguistically underrepresented domains, moving beyond the reliance on well-resourced modern language datasets.
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
arXiv:2609.00998v1 Announce Type: cross Abstract: Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings.
Abstract:Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2609.00998 [cs.CL]
(or arXiv:2609.00998v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.00998 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 · 299 words
Related coverage
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
Presentation: Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
InfoQ · Jun 10, 2026
The First Chatbot’s Multiple Personalities
IEEE Spectrum · Jul 15, 2026