Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings

• URL: http://arxiv.org/abs/2510.08774v1
• Date: Thu, 09 Oct 2025 19:45:54 GMT
• Title: Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
• Authors: Shikun Liu, Haoyu Wang, Mufei Li, Pan Li,
• Abstract summary: This paper introduces and systematically evaluates a new paradigm for generating structure-aware text embeddings.<n>We investigate two primary in-process methods: sequential concatenation and parallel caching.<n>Our analysis reveals critical trade-offs: sequential concatenation excels with noisy, moderate-length contexts, while parallel caching scales more effectively to long, high-signal contexts but is more susceptible to distractors.
• Score: 16.728984584960738
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that provides crucial context in many real-world datasets. This paper introduces and systematically evaluates a new paradigm for generating structure-aware text embeddings by integrating these structural relations directly into the LLM's internal encoding process, rather than relying on traditional post-hoc aggregation. We investigate two primary in-process methods: sequential concatenation and parallel caching. Through extensive zero-shot experiments across retrieval, clustering, classification, and recommendation tasks, we demonstrate that our structure-aware approaches consistently outperform both text-only and post-hoc baselines. Our analysis reveals critical trade-offs: sequential concatenation excels with noisy, moderate-length contexts, while parallel caching scales more effectively to long, high-signal contexts but is more susceptible to distractors. To address the challenge of noisy structural data, we also introduce and validate two effective techniques: Context Distillation and Semantic Balancing. This work provides the first comprehensive analysis of in-process structure-aware encoding, offering a blueprint for building more powerful and contextually aware embedding models.

Related papers

• BoundRL: Efficient Structured Text Segmentation through Reinforced Boundary Generation [26.825801831400003]
  BoundRL performs token-level text segmentation and label prediction for long structured texts.<n>Instead of generating complete contents for each segment, it generates only a sequence of starting tokens.<n>It reconstructs the complete contents by locating these tokens within the original texts.
  arXiv  Detail & Related papers  (2025-10-23T02:56:10Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning [29.722512436773638]
  We propose textscStructure-R1, a framework that transforms retrieved content into structured representations optimized for reasoning.<n>We show that textscStructure-R1 consistently achieves competitive performance with a 7B-scale backbone model.<n>Our theoretical analysis demonstrates how structured representations enhance reasoning by improving information density and contextual clarity.
  arXiv  Detail & Related papers  (2025-10-16T23:19:28Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Language Native Lightly Structured Databases for Large Language Model Driven Composite Materials Research [6.31777560888658]
  Preparation procedures of materials are often embedded narratively in experimental protocols, research articles, patents, and laboratory notes.<n>We reformulate this challenge into a text-reasoning problem through a framework centered on a text-first, lightly structured materials database.<n>We show how language-native data combined with LLM-based reasoning can significantly accelerate practical material preparation.
  arXiv  Detail & Related papers  (2025-09-07T15:15:55Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering [51.7493726399073]
  We present a discourse-aware hierarchical framework to enhance long document question answering.<n>The framework involves three key innovations: specialized discourse parsing for lengthy documents, LLM-based enhancement of discourse relation nodes, and structure-guided hierarchical retrieval.
  arXiv  Detail & Related papers  (2025-05-26T14:45:12Z)
• Enhancing Abstractive Summarization of Scientific Papers Using Structure Information [6.414732533433283]
  We propose a two-stage abstractive summarization framework that leverages automatic recognition of structural functions within scientific papers.<n>In the first stage, we standardize chapter titles from numerous scientific papers and construct a large-scale dataset for structural function recognition.<n>In the second stage, we employ Longformer to capture rich contextual relationships across sections and generating context-aware summaries.
  arXiv  Detail & Related papers  (2025-05-20T10:34:45Z)
• QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding [53.69841526266547]
  Fine-tuning a pre-trained Vision-Language Model with new datasets often falls short in optimizing the vision encoder.<n>We introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder.
  arXiv  Detail & Related papers  (2025-04-03T18:47:16Z)
• HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge [25.279158571663036]
  HyperG is a hypergraph-based generation framework aimed at enhancing Large Language Models' ability to process structured knowledge.<n>Specifically, HyperG first augments sparse data with contextual information, and incorporate a prompt-attentive hypergraph learning network to encode both the augmented information and the intricate structural relationships within the data.<n>To validate the effectiveness and generalization of HyperG, we conduct extensive experiments across two different downstream tasks requiring structured knowledge.
  arXiv  Detail & Related papers  (2025-02-25T11:47:32Z)
• Text Clustering with Large Language Model Embeddings [0.0]
  The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms.<n>Recent advancements in large language models (LLMs) have the potential to enhance this task.<n>Findings indicate that LLM embeddings are superior at capturing subtleties in structured language.
  arXiv  Detail & Related papers  (2024-03-22T11:08:48Z)
• Contextualization Distillation from Large Language Model for Knowledge Graph Completion [51.126166442122546]
  We introduce the Contextualization Distillation strategy, a plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models to transform compact, structural triplets into context-rich segments. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach.
  arXiv  Detail & Related papers  (2024-01-28T08:56:49Z)
• StructGPT: A General Framework for Large Language Model to Reason over Structured Data [117.13986738340027]
  We develop an emphIterative Reading-then-Reasoning(IRR) approach for solving question answering tasks based on structured data. Our approach can significantly boost the performance of ChatGPT and achieve comparable performance against the full-data supervised-tuning baselines.
  arXiv  Detail & Related papers  (2023-05-16T17:45:23Z)

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.