A semi-automated LLM-based framework for word sense disambiguation in Serbian

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.

Leveraging LLMs to Automatically Construct WordNets as Bilingual Resources

This paper proposes automated methods to construct high-quality WordNets using large language models (LLMs) to generate missing lemmas to address the synset shortfall in non-English and low-resource languages.

Bridges Between Words and Senses

The proposed k-Multilingual Concept model allows to uncover novel layers of lexical knowledge in the form of multifaceted conceptual links between naturally disambiguated sets of words.

WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution

Word-in-Context (WiC) remains challenging for language models, despite recent progress on lexical-semantic tasks. We hypothesise that this difficulty arises not only from comparing two contextual uses of a word, but also from the absence of an explicit sense inventory that specifies the relevant level of semantic granularity. We evaluate open LLMs on WiC and traditional Word Sense Disambiguation (WSD) under similar settings. We find that providing candidate senses, similar to what is done in traditional WSD, improves WiC performance in all settings. In general, explicit sense information helps models make more consistent and targeted judgements. Human evaluation further shows that many apparent WiC errors reflect label ambiguity or mismatches between model and annotator sense boundaries rather than simple failures of lexical understanding. In particular, results show that LLMs overthink the sense distinction often leading to errors based on overly fine-grained distinctions.

Arabic word sense disambiguation using the SenseGram framework

Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu

Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet their behaviour in low-resource languages remains poorly understood. In this work, we question how correct and reliable is the generation of multilingual LLMs when used for the task of story generation. We consider Urdu language as a representative low-resource language. We generate Urdu-Stories, a corpus of 93 stories generated using three contemporary LLMs (GPT-5.1, Qwen-3-Max, DeepSeek-3.1). We manually annotate the errors present in them under a nine-label linguistic, semantic, and cultural taxonomy. Our notable findings suggest that LLMs often make basic errors of grammar and semantics. The stories lack coherence, have unnatural repetition and show pervasive cultural shallowness. We further show using few-shot prompting that the cultural and context errors largely remain unresolved. Our findings highlight the limitations of current LLMs as a reliable source of content generation and information retrieval for low-resource languages.