Word Sense Disambiguation

Modals such as may and must can take on different senses depending on discourse context, alternating between root interpretations (e.g., permission, obligation) and epistemic interpretations (e.g., knowledge, belief). While modals are known to be notoriously difficult for children to acquire, limited research exists on whether language models (LMs) can reliably distinguish between different modal senses. We evaluate seven LMs that vary in architecture, size, and training data type using vector-based similarity and surprisal measures across four datasets. Specifically, we investigate whether LMs can leverage contextual information to disambiguate modal senses and whether their performance reflects the distribution of modal senses in their training data. We show that larger LMs trained on diverse text successfully leverage additional contextual information when available. In the absence of context, they tend to favor the dominant sense based on corpus statistics. Smaller developmentally plausible LMs, including those trained on child-directed language (CDL), fail to show consistent sensitivity to modal sense distinctions and do not benefit from context to the same degree.

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.

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.

In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three parameter sizes (GPT-2-Small-117M, Llama-3.2-3B, Qwen2.5-32B). For both homonyms and polysemes, we find that representations become maximally distinct in middle layers, then partially reconverge in late layers, while the KL divergence between their next-token predictions reaches its maximum in the final layers. The activation patching experiment provides causal evidence that late-layer representational differences directly determine outputs despite apparent increased similarity in embedding space. Our single-layer ablation experiment indicates that models achieve equivalent disambiguation despite qualitatively different layer-wise vulnerabilities. These findings offer a mechanism for recent observations where models' internal embedding similarities show low correlation with their behavioural outputs despite strong performance. The semantic distinctions therefore remain present but become increasingly invisible to similarity measures over the embeddings, with implications for embedding-based methods such as semantic search, retrieval, and clustering that rely on late-layer cosine similarity.

Many Bangla words are at once personal names and culturally loaded common nouns, "Maya" is both a girl's name and a word for affectionate compassion. Choosing the right reading demands cultural knowledge that is scarce in the pretraining data of modern language models. We introduce Culturally Entangled Homograph (CEH) disambiguation and build a Bangla benchmark of 1,516 expert-verified sentences (3,032 labelled occurrences) in which one word appears twice with two distinct readings, each labelled with a culturally grounded category and an explanation of the reasoning behind it. Across open- and closed-source models, we find a systematic dominant-meaning bias: models default to the common-noun sense and overlook the name. A Bangla-specific model fails under every prompting regime we test, showing that language-specific pretraining alone does not confer cultural grounding. We further show that contrastive chain-of-thought prompting can sharply reduce this bias without training, and that distilling cultural explanations teaches small (1-3B) models to reason toward the correct reading rather than memorise labels, cutting dominant-meaning bias from as high as 100% to under 5% and turning the failed Bangla-specific model into our strongest system. Dataset and code are available at https://github.com/ashuvo25/BanglaCEH.

Automatic semantic change detection aims to identify how word meanings shift over time, offering insights into both linguistic and societal change. Despite recent progress in computational lexical semantic change (LSC), existing benchmarks and methods struggle to capture bi-directional semantic change, particularly cases where words simultaneously gain and lose senses. This problem is especially challenging for words that have both slang and standard meanings. To address these gaps, we introduce two complementary benchmark datasets. The Bi-Directional Lexical Semantic Change (BD-LSC) dataset captures sense gain, sense loss, and stability across three time periods, enabling the study of complex semantic trajectories. The SlangTrack Word Sense Disambiguation (ST-WSD) dataset provides fine-grained, instance-level sense annotations for words combining slang and standard usages, supporting systematic benchmarking of WSD and semantic change detection models. Using these benchmarks, we systematically evaluate models across different methodological families: unsupervised clustering using contextualised embeddings, supervised machine learning, transformer-based models, and state-of-the-art large language models. Among the evaluated systems, the few-shot GPT-4o model achieved the strongest aggregate performance on Exact Sense Match (ESM) and multi-label accuracy; however, Macro-F1 scores near 0.5 across all systems show that rare slang senses remain difficult, which we identify as the central open challenge.

Sense representations (explicit, per-token meaning decompositions) are useful for disambiguation, steering, and cross-lingual alignment, but existing approaches require models to be pretrained with sense structure baked in. We introduce ACROS, which induces an explicit sense pathway into a frozen pretrained decoder LM through a gated residual addition. On SmolLM2-360M, ACROS preserves base LM quality while supporting three uses of the same induced variables: zero-shot word-sense disambiguation (64.95 F1 on Raganato ALL, competitive with the WordNet first-sense heuristic), low-KL lexical steering across 5,161 CoInCo cases where a simple non-oracle proxy recovers about 90% of positive shifts, and SENSIA cross-lingual adaptation to four languages (mean R@1 0.988, target FLORES PPL 7.94). ACROS makes sense representations an inducible interface for ordinary pretrained LMs.

We describe a new sense-tagged corpus for word sense disambiguation. The corpus is constituted of instances of 20 French polysemous verbs. Each verb instance is annotated with three sense labels: (1) the actual translation of the verb in the english version of this instance in a parallel corpus, (2) an entry of the verb in a computational dictionary of French (the Lexicon-Grammar tables) and (3) a fine-grained sense label resulting from the concatenation of the translation and the Lexicon-Grammar entry.

We study Relational Semantic Decomposition, abbreviated as RSD, as a moving local triangular chart audit for language-model hidden states. For repeated occurrences of one target word, RSD fits a shared three-anchor membership chart $S_t$ at layer or token-time $t$. The hidden-state channel uses $X_t\approx S_tC_t$; the invariant readout $M_t=S_tS_t^\top$ is the induced occurrence co-membership relation, and $R_t=X_t-S_tC_t$ records what the fitted root chart leaves outside the chart. The broader joint audit reuses the same membership chart for relation data, $A_t\approx S_tB_tS_t^\top$, such as an attention-derived occurrence relation. The current GPT-2 evidence is the $X$-channel hidden-state audit with Word-in-Context labels used as an external same-sense versus different-sense reference relation. On full WiC train, the root chart passes 16 of 53 eligible target words; this is audit coverage, not GPT-2 task accuracy. Token-time and pair-level diagnostics show the main regimes: make and break align at the target state, drive and stay improve after right context in small-count exploratory cases, and play remains a localized root-chart failure whose final same-sense pairs are not closer and have larger residual discrepancy. The resulting claim is diagnostic: RSD reports where a sense relation is visible in root co-membership and which failures become residual branch candidates or attention-channel obligations.

Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large Language Models (LLMs) can effectively disambiguate, their practical applicability in real-world narrative contexts remains underexplored. SemEval-2026 Task 5 addresses this gap by introducing a task that predicts the human-perceived plausibility of a word sense within a short story. In this work, we propose an LLM-based framework for plausibility scoring of homonymous word senses in narrative texts using a structured reasoning mechanism. We examine the impact of fine-tuning low-parameter LLMs with diverse reasoning strategies, alongside dynamic few-shot prompting for large-parameter models, on accurate sense identification and plausibility estimation. Our results show that commercial large-parameter LLMs with dynamic few-shot prompting closely replicate human-like plausibility judgments. Furthermore, model ensembling slightly improves performance, better simulating the agreement patterns of five human annotators compared to single-model predictions

If the same neuron activates for both "lender" and "riverside," standard metrics attribute the overlap to superposition--the neuron must be compressing two unrelated concepts. This work explores how much of the overlap is due a lexical confound: neurons fire for a shared word form (such as "bank") rather than for two compressed concepts. A 2x2 factorial decomposition reveals that the lexical-only condition (same word, different meaning) consistently exceeds the semantic-only condition (different word, same meaning) across models spanning 110M-70B parameters. The confound carries into sparse autoencoders (18-36% of features blend senses), sits in <=1% of activation dimensions, and hurts downstream tasks: filtering it out improves word sense disambiguation and makes knowledge edits more selective (p = 0.002).

Social media text shows promise for monitoring trends in the opioid overdose crisis; however, the overwhelming majority of social media text is unrelated to opioids. When leveraging social media text to monitor trends in the ongoing opioid overdose crisis, a common strategy for identifying relevant content is to use a lexicon of opioid-related terms as inclusion criteria. However, many slang terms for opioids, such as "smack" or "blues," have common non-opioid meanings, making them ambiguous. The advanced textual reasoning capability of large language models (LLMs) presents an opportunity to disambiguate these slang terms at scale. We present three tasks on which to evaluate four state-of-the-art LLMs (GPT-4, GPT-5, Gemini 2.5 Pro, and Claude Sonnet 4.5): a lexicon-based setting, in which the LLM must disambiguate a specific term within the context of a given post; a lexicon-free setting, in which the LLM must identify opioid-related posts from context without a lexicon; and an emergent slang setting, in which the LLM must identify opioid-related posts with simulated new slang terms. All four LLMs showed excellent performance across all tasks. In both subtasks of the lexicon-based setting, LLM F1 scores ("fenty" subtask: 0.824-0.972; "smack" subtask: 0.540-0.862) far exceeded those of the best lexicon strategy (0.126 and 0.009, respectively). In the lexicon-free task, LLM F1 scores (0.544-0.769) surpassed those of lexicons (0.080-0.540), and LLMs demonstrated uniformly higher recall. On emergent slang, all LLMs had higher accuracy (average: 0.784), F1 score (average: 0.712), precision (average: 0.981), and recall (average: 0.587) than the two lexicons assessed. Our results show that LLMs can be used to identify relevant content for low-prevalence topics, including but not limited to opioid references, enhancing data provided to downstream analyses and predictive models.

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (<4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that Chain-of-Thought (CoT)-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen "Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.