Large language models (LLMs) rely heavily on sampling methods to generate diverse and high-quality text.While existing sampling methods like top-p and min-p have identified the detrimental effects of low-probability tails in LLMs’ outputs, they still fail to effectively distinguish between diversity and noise. This limitation stems from their reliance on probability-based metrics that are inherently sensitive to temperature scaling. Through empirical and theoretical analysis, we make two key discoveries: (1) the pre-softmax logits exhibit a clear statistical separation between informative tokens and noise, and (2) we prove the mathematical equivalence of min-p and top-(1-p) under uniform distribution over logits. These findings motivate the design of top-n𝜎, a novel sampling method that identifies informative tokens by eliminating noise directly in logit space.Unlike existing methods that become unstable at high temperatures, top-n𝜎 achieves temperature-invariant token selection while preserving output diversity. Extensive experiments across reasoning and creative writing tasks demonstrate that our method consistently outperforms existing approaches, with particularly significant improvements in high-temperature settings.

Traditional word embedding approaches learn semantic information at word level while ignoring the meaningful internal structures of words like morphemes. Furthermore, existing morphology-based models directly incorporate morphemes to train word embeddings, but still neglect the latent meanings of morphemes. In this paper, we explore to employ the latent meanings of morphological compositions of words to train and enhance word embeddings. Based on this purpose, we propose three Latent Meaning Models (LMMs), named LMM-A, LMM-S and LMM-M respectively, which adopt different strategies to incorporate the latent meanings of morphemes during the training process. Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models. The results demonstrate that our models outperform the baselines on five word similarity datasets. On Wordsim-353 and RG-65 datasets, our models nearly achieve 5% and 7% gains over the classic CBOW model, respectively. For the syntactic analogy and text classification tasks, our models also surpass all the baselines including a morphology-based model.