Vec2Summ: Text Summarization via Probabilistic Sentence Embeddings

• URL: http://arxiv.org/abs/2508.07017v1
• Date: Sat, 09 Aug 2025 15:31:02 GMT
• Title: Vec2Summ: Text Summarization via Probabilistic Sentence Embeddings
• Authors: Mao Li, Fred Conrad, Johann Gagnon-Bartsch,
• Abstract summary: Vec2Summ represents a document collection using a single mean vector in the semantic embedding space.<n>We reconstruct fluent summaries using a generative language model.<n>Vec2Summ produces coherent summaries for topically focused, order-invariant corpora.
• Score: 2.2029818765681086
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We propose Vec2Summ, a novel method for abstractive summarization that frames the task as semantic compression. Vec2Summ represents a document collection using a single mean vector in the semantic embedding space, capturing the central meaning of the corpus. To reconstruct fluent summaries, we perform embedding inversion -- decoding this mean vector into natural language using a generative language model. To improve reconstruction quality and capture some degree of topical variability, we introduce stochasticity by sampling from a Gaussian distribution centered on the mean. This approach is loosely analogous to bagging in ensemble learning, where controlled randomness encourages more robust and varied outputs. Vec2Summ addresses key limitations of LLM-based summarization methods. It avoids context-length constraints, enables interpretable and controllable generation via semantic parameters, and scales efficiently with corpus size -- requiring only $O(d + d^2)$ parameters. Empirical results show that Vec2Summ produces coherent summaries for topically focused, order-invariant corpora, with performance comparable to direct LLM summarization in terms of thematic coverage and efficiency, albeit with less fine-grained detail. These results underscore Vec2Summ's potential in settings where scalability, semantic control, and corpus-level abstraction are prioritized.

Related papers

• Sparse Semantic Dimension as a Generalization Certificate for LLMs [53.681678236115836]
  We introduce the Sparse Semantic Dimension (SSD), a complexity measure derived from the active feature vocabulary of a Sparse Autoencoder (SAE) trained on the model's layers.<n>We validate this framework on GPT-2 Small and Gemma-2B, demonstrating that our bound provides non-vacuous certificates at realistic sample sizes.
  arXiv  Detail & Related papers  (2026-02-11T21:45:18Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• DVD: A Robust Method for Detecting Variant Contamination in Large Language Model Evaluation [24.086354908256293]
  textbfDVD is a single-sample detector that models the local output distribution induced by temperature sampling.<n>We construct the first benchmark for variant contamination across two domains Omni-MATH and SuperGPQA.<n>textbfDVD consistently outperforms perplexity-based, Min-$k$%++, edit-distance (CDD), and embedding-similarity baselines.
  arXiv  Detail & Related papers  (2026-01-08T12:48:40Z)
• Syntactic Control of Language Models by Posterior Inference [53.823006836309695]
  Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability.<n>We argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation.<n>Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure.
  arXiv  Detail & Related papers  (2025-06-08T14:01:34Z)
• Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment [69.67015515485349]
  We propose AutoRegEmbed, a contrastive learning method built on embedding conditional probability distributions.<n>We show that our method significantly outperforms traditional contrastive learning approaches.
  arXiv  Detail & Related papers  (2025-02-17T03:36:25Z)
• Summaries as Centroids for Interpretable and Scalable Text Clustering [0.0]
  We introduce k-NLPmeans and k-LLMmeans, text-clustering variants of k-means that periodically replace numeric centroids with textual summaries.<n>The key idea, summary-as-centroid, retains k-means assignments in embedding space while producing human-readable, auditable cluster prototypes.
  arXiv  Detail & Related papers  (2025-02-12T19:50:22Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval [54.66399120084227]
  We propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM. Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
  arXiv  Detail & Related papers  (2023-05-18T15:43:09Z)
• Contrastive Conditional Neural Processes [45.70735205041254]
  Conditional Neural Processes(CNPs) bridge neural networks with probabilistic inference to approximate functions of Processes under meta-learning settings. Two auxiliary contrastive branches are set up hierarchically, namely in-instantiation temporal contrastive learning(tt TCL) and cross-instantiation function contrastive learning(tt FCL) We empirically show that tt TCL captures high-level abstraction of observations, whereas tt FCL helps identify underlying functions, which in turn provides more efficient representations.
  arXiv  Detail & Related papers  (2022-03-08T10:08:45Z)
• Reinforcing Semantic-Symmetry for Document Summarization [15.113768658584979]
  Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. This paper introduces a new textbfreinforcing stextbfemantic-textbfsymmetry learning textbfmodel is proposed for document summarization. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent.
  arXiv  Detail & Related papers  (2021-12-14T17:41:37Z)
• Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction [31.648764677078837]
  Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. We model these two aspects in an unsupervised objective function, consisting of language modeling and semantic similarity metrics. Our proposed method achieves a new state-of-the art for unsupervised sentence summarization according to ROUGE scores.
  arXiv  Detail & Related papers  (2020-05-04T19:01:55Z)
• Exploring Explainable Selection to Control Abstractive Summarization [51.74889133688111]
  We develop a novel framework that focuses on explainability. A novel pair-wise matrix captures the sentence interactions, centrality, and attribute scores. A sentence-deployed attention mechanism in the abstractor ensures the final summary emphasizes the desired content.
  arXiv  Detail & Related papers  (2020-04-24T14:39:34Z)
• Interpretable Multi-Headed Attention for Abstractive Summarization at Controllable Lengths [14.762731718325002]
  Multi-level Summarizer (MLS) is a supervised method to construct abstractive summaries of a text document at controllable lengths. MLS outperforms strong baselines by up to 14.70% in the METEOR score.
  arXiv  Detail & Related papers  (2020-02-18T19:40:20Z)

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.