arXiv:2608. 19472v1 Announce Type: new Abstract: Lexical semantic change (LSC) is commonly modelled through vector-space representations, but these approaches often provide limited insight into which aspects of usage are changing.
The paper tackles the problem of automatically generating dictionary definitions for learner’s dictionaries, focusing on simplicity and clarity. It introduces a new evaluation framework that uses large language models as judges, validated against human annotators with comparable agreement levels. The authors also present an iterative simplification approach that produces definitions scoring highly on their criteria and exhibiting lexical simplicity.
The BD-LSC dataset introduces a bi‑directional lexical semantic change benchmark that tracks sense gain, loss, and stability across three time periods, while the ST‑WSD dataset offers fine‑grained, instance‑level sense annotations for words that blend slang and standard usage. These resources enable systematic evaluation of diverse models—including unsupervised clustering, supervised learning, transformer‑based approaches, and large language models—on tasks such as exact sense matching and multi‑label accuracy. The evaluation shows that few‑shot GPT‑4o performs best overall, yet all systems struggle with rare slang senses, highlighting a key open challenge in the field.
arXiv:2609.08609v2 Announce Type: replace Abstract: Tracking semantic change in low-resource languages across extensive historical timelines presents significant challenges due to data scarcity and t...
The paper investigates how climate disclosure classification performs when the source of the text changes, such as moving from annual reports to press releases or earnings calls. It evaluates three adaptation strategies—definitions, examples, and fine‑tuning—across eleven large language models using two corpora that share the same label space but differ in source. The study finds that while all strategies improve cross‑source performance on average, the most effective in‑source methods (similarity‑based retrieval and LoRA fine‑tuning) lose much of their advantage when the source shifts, whereas simpler approaches like randomly selected few‑shot examples and definition‑based prompts remain more robust, especially when definitions match the granularity of the target text.
arXiv:2606. 23533v2 Announce Type: replace Abstract: Recent large language models (LLMs) are good at general text generation, but it is still hard to use them for domain-specific data generation because the output must follow strict formatting and structural rules.
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.
arXiv:2507.09601v3 Announce Type: replace-cross Abstract: Financial text embeddings must distinguish changes in event status, perspective, and obligations even when passages share similar wording. NM...
arXiv:2608.04186v3 Announce Type: replace Abstract: This paper presents a conceptual framework for developing an electronic explanatory dictionary of the Tajik language using large language models (L...
The study investigates whether contextual embeddings can detect meaning changes in scientific terminology beyond traditional frequency counts. Using Astrophysics and NLP corpora from 2010 to 2024, the authors extract candidate terms with KeyBERT, filter for significant frequency rises, and then evaluate semantic drift via multiple embedding‑based metrics. Results show that frequency methods slightly outperform embedding metrics in aligning with expert judgments, yet embedding‑only detections (e.g., "primordial black holes") reveal critical conceptual shifts missed by frequency alone, suggesting complementary value.
The study introduces a panel of three large language models that score each sentence of political manifestos on environmental protection and climate change, producing averaged manifesto-level ratings. Applied to 41 2024 European Parliament election manifestos, the model’s rankings align closely with the Chapel Hill Expert Survey but tend to rate parties as greener than experts, suggesting a gap between promises and practice. The approach offers a low‑cost, multilingual, and reproducible alternative to traditional expert surveys and hand‑coding, with inter‑model disagreement serving as a built‑in reliability check.
The paper presents the CDSP (context-conditional deliberation signal pipeline), which transforms investment committee meeting transcripts into structured predictive features. CDSP segments transcripts into topical chunks, assigns asset‑class context labels via a large language model, maps financial keywords to a taxonomy, and adds sentiment polarity and mention frequency features. Using these engineered features on 48 monthly meetings, the best model—combining sentence embeddings with CDSP features—achieves 73% accuracy and a 0.73 F1 score, outperforming a simple stock‑choice baseline, though the improvement is not statistically significant.