Context-Aware Detection of Specialized Language

Where Were They? Person-Place Relation Extraction in Multilingual Historical Archives ⋆

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

Inspicio is presented, 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.

MGAL: A Multilingual Granularity-Aware Long-Context Benchmark

MGAL is the first multilingual, granularity- and position-aware long-context benchmark, constructed from United Nations reports spanning 8K to 128K tokens across the six official UN languages, and finds that LLMs perform well at word-level tasks but struggle with coarser-grained ones.

From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

A framework is proposed that identifies which label pairs the model struggles to distinguish, expands the candidate set to include confusable labels, and generates targeted rules to differentiate between similar candidates, which requires no fine-tuning and transfers to smaller, cheaper models.

Using Large Language Models for Automated Corpus Annotation and Linguistic Analysis: A Critical Methodological Framework

This article argues against unvalidated full automation and proposes selective automation, disagreement-based human adjudication, model/version documentation, and preservation of raw outputs for corpus research and develops a validated human–LLM workflow for corpus research.

Lost in Translation, Found in Summary: Summary-Driven Supervision for Cross-Language Code Retrieval

Cross-language code retrieval (CLCR) is critical to modern software development, and recent studies have shown that contrastive learning is an effective way to learn cross-language code semantics. However, these methods are still limited by two fundamental challenges. First, they rely on online judge platforms or multi...