From the New World of Word Embeddings: A Comparative Study of Small-World Lexico-Semantic Networks in LLMs

• URL: http://arxiv.org/abs/2502.11380v2
• Date: Mon, 19 May 2025 17:17:00 GMT
• Title: From the New World of Word Embeddings: A Comparative Study of Small-World Lexico-Semantic Networks in LLMs
• Authors: Zhu Liu, Ying Liu, KangYang Luo, Cunliang Kong, Maosong Sun,
• Abstract summary: Lexico-semantic networks represent words as nodes and their semantic relatedness as edges.<n>We construct lexico-semantic networks from the input embeddings of decoder-only large language models.<n>Our results show that these networks exhibit small-world properties, characterized by high clustering and short path lengths.
• Score: 47.52062992606549
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Lexico-semantic networks represent words as nodes and their semantic relatedness as edges. While such networks are traditionally constructed using embeddings from encoder-based models or static vectors, embeddings from decoder-only large language models (LLMs) remain underexplored. Unlike encoder models, LLMs are trained with a next-token prediction objective, which does not directly encode the meaning of the current token. In this paper, we construct lexico-semantic networks from the input embeddings of LLMs with varying parameter scales and conduct a comparative analysis of their global and local structures. Our results show that these networks exhibit small-world properties, characterized by high clustering and short path lengths. Moreover, larger LLMs yield more intricate networks with less small-world effects and longer paths, reflecting richer semantic structures and relations. We further validate our approach through analyses of common conceptual pairs, structured lexical relations derived from WordNet, and a cross-lingual semantic network for qualitative words.

Related papers

• Interpreting the Linear Structure of Vision-language Model Embedding Spaces [15.065914257384204]
  We train and release sparse autoencoders (SAEs) on the embedding spaces of four vision-language models. We find that SAEs are better at reconstructing the real embeddings, while also able to retain the most sparsity. We also show that the key commonly-activating concepts extracted by SAEs are remarkably stable across runs.
  arXiv  Detail & Related papers  (2025-04-16T01:40:06Z)
• A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs [50.982315553104975]
  Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms.<n>Most SMMs are manually built by human experts using bottom-up procedures.<n>We propose a novel graph-based algorithm that automatically generates conceptual spaces and SMMs in a top-down manner.
  arXiv  Detail & Related papers  (2024-12-02T12:06:41Z)
• Tomato, Tomahto, Tomate: Measuring the Role of Shared Semantics among Subwords in Multilingual Language Models [88.07940818022468]
  We take an initial step on measuring the role of shared semantics among subwords in the encoder-only multilingual language models (mLMs) We form "semantic tokens" by merging the semantically similar subwords and their embeddings. inspections on the grouped subwords show that they exhibit a wide range of semantic similarities.
  arXiv  Detail & Related papers  (2024-11-07T08:38:32Z)
• Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources [11.257738983764499]
  Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. We enhance "modern" supervised WSD models exploiting two popular SLRs: WordNet and WordNet Domains. We study the effect of different types of semantic features, investigating their interaction with local contexts encoded by means of mixtures of Word Embeddings or Recurrent Neural Networks.
  arXiv  Detail & Related papers  (2024-02-20T13:47:51Z)
• Autoencoder-Based Domain Learning for Semantic Communication with Conceptual Spaces [1.7404865362620803]
  We develop a framework for learning a domain of a conceptual space model using only the raw data with high-level property labels. In experiments using the MNIST and CelebA datasets, we show that the domains learned using the framework maintain semantic similarity relations and possess interpretable dimensions.
  arXiv  Detail & Related papers  (2024-01-29T21:08:33Z)
• Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning [32.178931149612644]
  In-context learning enables language models to adapt to downstream data or incorporate tasks by few samples as demonstrations within the prompts. However, the performance of in-context learning can be unstable depending on the quality, format, or order of demonstrations. We propose a novel approach "vocabulary-defined semantics"
  arXiv  Detail & Related papers  (2024-01-29T14:29:48Z)
• Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing [2.5002227227256864]
  We present experiments with semantic structural probing, a method for studying sentence-level representations. We apply our method to language models from different families (encoder-only, decoder-only, encoder-decoder) and of different sizes in the context of two tasks. We find that model families differ substantially in their performance and layer dynamics, but that the results are largely model-size invariant.
  arXiv  Detail & Related papers  (2023-10-18T12:32:07Z)
• Probing Large Language Models from A Human Behavioral Perspective [24.109080140701188]
  Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. The understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention (MHSA) remains largely unexplored.
  arXiv  Detail & Related papers  (2023-10-08T16:16:21Z)
• Topological properties and organizing principles of semantic networks [3.8462776107938317]
  We study the properties of semantic networks from ConceptNet, defined by 7 semantic relations from 11 different languages. We find that semantic networks have universal basic properties: they are sparse, highly clustered, and many exhibit power-law degree distributions. In some networks the connections are similarity-based, while in others the connections are more complementarity-based.
  arXiv  Detail & Related papers  (2023-04-24T11:12:21Z)
• Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning [68.63380306259742]
  Despite its promising potential, semantic communications and semantic-aware networking are still at their infancy. We propose a novel reasoning-based implicit semantic-aware communication network architecture that allows multiple tiers of CDC and edge servers to collaborate. We introduce a new multi-layer representation of semantic information taking into consideration both the hierarchical structure of implicit semantics as well as the personalized inference preference of individual users.
  arXiv  Detail & Related papers  (2022-10-28T13:26:08Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)
• TeKo: Text-Rich Graph Neural Networks with External Knowledge [75.91477450060808]
  We propose a novel text-rich graph neural network with external knowledge (TeKo) We first present a flexible heterogeneous semantic network that incorporates high-quality entities. We then introduce two types of external knowledge, that is, structured triplets and unstructured entity description.
  arXiv  Detail & Related papers  (2022-06-15T02:33:10Z)
• Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution [124.99894592871385]
  We present a large-scale comparative study of lexical substitution methods employing both old and most recent language models. We show that already competitive results achieved by SOTA LMs/MLMs can be further substantially improved if information about the target word is injected properly.
  arXiv  Detail & Related papers  (2022-06-07T16:16:19Z)
• Integrating Language Guidance into Vision-based Deep Metric Learning [78.18860829585182]
  We propose to learn metric spaces which encode semantic similarities as embedding space. These spaces should be transferable to classes beyond those seen during training. This causes learned embedding spaces to encode incomplete semantic context and misrepresent the semantic relation between classes.
  arXiv  Detail & Related papers  (2022-03-16T11:06:50Z)
• Text analysis and deep learning: A network approach [0.0]
  We propose a novel method that combines transformer models with network analysis to form a self-referential representation of language use within a corpus of interest. Our approach produces linguistic relations strongly consistent with the underlying model as well as mathematically well-defined operations on them. It represents, to the best of our knowledge, the first unsupervised method to extract semantic networks directly from deep language models.
  arXiv  Detail & Related papers  (2021-10-08T14:18:36Z)
• Learning low-rank latent mesoscale structures in networks [1.1470070927586016]
  We present a new approach for describing low-rank mesoscale structures in networks. We use several synthetic network models and empirical friendship, collaboration, and protein--protein interaction (PPI) networks. We show how to denoise a corrupted network by using only the latent motifs that one learns directly from the corrupted network.
  arXiv  Detail & Related papers  (2021-02-13T18:54:49Z)
• Model Choices Influence Attributive Word Associations: A Semi-supervised Analysis of Static Word Embeddings [0.0]
  This work aims to assess attributive word associations across five different static word embedding architectures. Our results reveal that the choice of the context learning flavor during embedding training (CBOW vs skip-gram) impacts the word association distinguishability and word embeddings' sensitivity to deviations in the training corpora.
  arXiv  Detail & Related papers  (2020-12-14T22:27:18Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.