# Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages

arXiv: https://arxiv.org/abs/2609.00998 · HTML: https://mlsanity.com/paper/2609.00998/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Exploring the Word Sense Disambiguation Capabilities of Large Language Models](https://mlsanity.com/paper/2503.08662/) (2025)
- [Do Large Language Models Understand Word Senses?](https://mlsanity.com/paper/2509.13905/) (2025)
- [Word Sense Linking: Disambiguating Outside the Sandbox](https://mlsanity.com/paper/2412.09370/) (2024)

## Abstract (arXiv)

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.