Large language models learn word meanings through distributional semantics (i.e., patterns in text), and distribution does not always capture information about taxonomy and function, which are essential to human representations of word meaning. However, sound and spelling often conveys such information, and language models decompose many words into subword tokens, which may identify category markers. For example, GPT-5 segments fluorine and bromine into fluor + ine and brom + ine, which share the category marker ine. We provide evidence that, across 18 languages, shared tokens predict greater semantic priming effects in humans (e.g., people recognize bromine faster after reading fluorine), beyond what distributional similarity explains. Furthermore, across seven languages, shared tokens boost semantic priming beyond what shared morphemes explain. This suggests that subword tokens could help language models arrive at human-like representations of word meanings. However, we also provide evidence that the trend towards larger vocabularies of tokens obscures category markers, and even when language models have access to subword tokens, they underestimate the semantic relatedness of words that share tokens.

Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet comparing such explanations remains challenging. Existing soft-perturbation faithfulness metrics, such as Soft-NC and Soft-NS, can conflate attribution quality with the number of words retained during perturbation: attribution methods with larger average scores may keep more words and therefore obtain inflated scores. To address this issue, we propose 𝜋-Soft-NC and 𝜋-Soft-NS, an evaluation framework that compares attribution methods under the same expected retaining probability, thus controlling the number of retained words. We further introduce Grad-ELLM, a gradient-based attribution method tailored to autoregressive decoder-only LLMs, which combines gradient-derived channel importance with attention-derived token importance at each decoding step. Experiments on classification and open-generation tasks with Llama and Mistral show that Grad-ELLM achieves strong comprehensiveness-oriented faithfulness under 𝜋-Soft-NC, while there is no dominant method under 𝜋-Soft-NS. Our evaluation metric serves as a controlled evaluation framework to compare XAI methods for LLMs, which will support progress in the field.