arXiv AI September 2, 2026 By Michele Ciletti

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

Inspicio is an open‑vocabulary pipeline that links tokens in historical or low‑resource languages to synsets in the Open English WordNet without needing a source‑language sense inventory. It uses an instruction‑tuned LLM to generate two English translations, candidate dictionary definitions, and English lemmas, then performs hybrid retrieval combining dense definition similarity, sparse lemma matching, and Maximal Marginal Relevance re‑ranking. Evaluated on Latin, Ancient Greek, PREMOVE, and Italian data, the best configuration achieves 96% Recall@50 on a perception‑verb test set and remains competitive in out‑of‑domain and cross‑lingual scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Sep 1

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

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 i...

llms rag

arXiv AI

Jun 10

Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection

arXiv:2604. 14397v2 Announce Type: replace-cross Abstract: We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation.

By David Basil, Chirooth Girigowda, Bradley Hauer, Sahir Momin, Ning Shi, Grzegorz Kondrak

llms nlp

arXiv AI

Oct 1

Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning

The paper introduces the problem of cross‑lingual loopholes in large language model (LLM) unlearning, where forgetting a fact in one language can leave it accessible in others. It presents a new 174‑language benchmark, the Cross‑Lingual Unlearning Tensor, and proposes COVER, a method that selects a subset of source languages to maximize unlearning coverage under a language budget. Experiments show COVER reduces residual knowledge by 7.8–27.3% compared to uniform selection and works on both synthetic and real low‑resource news data.

By Tyler Skow, Shravan Chaudhari, Rama Chellappa, Abhay Yadav

llms benchmarks

arXiv Computation and Language

Sep 1

Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature

The paper introduces Loci Similes, a benchmark for detecting intertextual links in Latin literature. It provides a curated dataset of about 176,000 text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing source. Baselines for retrieval and classification are established using both lexical methods and pretrained encoder language models.

By Julian Schelb, Michael Wittweiler, Marie Revellio, Barbara Feichtinger, Andreas Spitz

llms benchmarks

arXiv AI

Aug 6

Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

arXiv:2608. 05138v1 Announce Type: cross Abstract: Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval-augmented generation (RAG) in legal, energy, financial, and medical applications.

By Ayoub Kirouane, Christos Petrocheilos

rag fine-tuning benchmarks

arXiv Computation and Language

Sep 1

Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study

arXiv:2608.28776v1 Announce Type: new Abstract: Multilingual sentence embeddings are increasingly used to estimate semantic similarity across languages, yet their sensitivity to fine-grained translat...

By Eleftherios Kalogeros, Athanasios Ntalakas, Manolis Gergatsoulis, Paschalis Nikolaou, Sotiria-Lito Alexaki

rag

One email a morning, machine-written

Related stories

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

Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection

Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning

Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature

Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study