ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement

• URL: http://arxiv.org/abs/2606.18850v1
• Date: Wed, 17 Jun 2026 09:31:07 GMT
• Title: ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement
• Abstract summary: We propose a hierarchical reflective graph-based framework that emulates a student-teacher writing process for fluent and faithful scientific summarization.<n>ScholarSum first organizes the document into a hierarchical knowledge graph by segmenting it into semantically coherent units.<n>To ensure factual consistency, a teacher-like reviewer then iteratively examines the draft, identifies unsupported content, and prompts targeted re-retrieval and rewriting.
• Score: 9.620629066606197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Abstractive summarization plays a crucial role in enabling efficient understanding of scientific literature, yet it inherently demands both linguistic fluency and factual faithfulness. Existing approaches often fail to reconcile these two requirements. Extractive methods rely on rigid sentence splicing that disrupts macro-level logical coherence, while large language model (LLM)-based generative approaches, despite mastering linguistic fluency, exhibit limited factual consistency. In this work, we propose ScholarSum, a hierarchical reflective graph-based framework that emulates a student-teacher writing process for fluent and faithful scientific summarization. ScholarSum first organizes the document into a hierarchical knowledge graph by segmenting it into semantically coherent units, whose multi-layered community structure captures global logic and macro-level themes. Guided by this global structure, the student generates an initial draft, which is subsequently refined through fine-grained evidence retrieval. To ensure factual consistency, a teacher-like reviewer then iteratively examines the draft, identifies unsupported content, and prompts targeted re-retrieval and rewriting until the summary meets rigorous quality standards. Extensive experiments demonstrate that ScholarSum significantly outperforms previous baselines in terms of both completeness and faithfulness. Our code is available at https://github.com/Xiaoyu-Tao/ScholarSum.

Related papers

• LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation [57.70907667652966]
  Introduction writing is especially challenging, which demands logical soundness and verifiable faithfulness.<n>Most AI-assisted methods treat the task as text generation instead of reasoning and structuring, leading to severe drawbacks.<n>We propose LECTOR, a novel Logic-Expression Co-Reinforcement Learning framework that can strictly follow the scientist's logic, add high-quality citations and keep structured expressions.
  arXiv  Detail & Related papers  (2026-05-25T15:41:16Z)
• General Machine Learning: Theory for Learning Under Variable Regimes [2.538209532048866]
  We study learning under regime variation, where the learner, its memory state, and the evaluative conditions may evolve over time.<n>The paper develops a regime-varying framework centered on admissible transport, protected-core preservation, and evaluator-aware learning evolution.
  arXiv  Detail & Related papers  (2026-03-24T13:58:31Z)
• AWARE, Beyond Sentence Boundaries: A Contextual Transformer Framework for Identifying Cultural Capital in STEM Narratives [0.5514573274011145]
  AWARE is a framework that attempts to improve a transformer model's awareness for this nuanced task.<n>We show that by making the model explicitly aware of the properties of the input, AWARE outperforms a strong baseline by 2.1 percentage points in Macro-F1.<n>This work provides a robust and generalizable methodology for any text classification task in which meaning depends on the context of the narrative.
  arXiv  Detail & Related papers  (2025-10-06T16:19:57Z)
• Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking [23.23119083861653]
  SemRank is an effective and efficient paper retrieval framework.<n>It combines query understanding with a concept-based semantic index.<n> Experiments show that SemRank consistently improves the performance of various base retrievers.
  arXiv  Detail & Related papers  (2025-05-27T22:49:18Z)
• 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)
• Taxonomy Tree Generation from Citation Graph [15.188580557890942]
  HiGTL is a novel end-to-end framework guided by human-provided instructions or preferred topics.<n>We develop a novel taxonomy node verbalization strategy that iteratively generates central concepts for each cluster.<n>Experiments demonstrate that HiGTL effectively produces coherent, high-quality concept.
  arXiv  Detail & Related papers  (2024-10-02T13:02:03Z)
• Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level [3.7651378994837104]
  Long input hinders simultaneous modeling of both global high-order relations between sentences and local intra-sentence relations. We propose HAESum, a novel approach utilizing graph neural networks to model documents based on their hierarchical discourse structure. We validate our approach on two benchmark datasets, and the experimental results demonstrate the effectiveness of HAESum.
  arXiv  Detail & Related papers  (2024-05-16T15:46:30Z)
• Hierarchical Indexing for Retrieval-Augmented Opinion Summarization [60.5923941324953]
  We propose a method for unsupervised abstractive opinion summarization that combines the attributability and scalability of extractive approaches with the coherence and fluency of Large Language Models (LLMs) Our method, HIRO, learns an index structure that maps sentences to a path through a semantically organized discrete hierarchy. At inference time, we populate the index and use it to identify and retrieve clusters of sentences containing popular opinions from input reviews.
  arXiv  Detail & Related papers  (2024-03-01T10:38:07Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback [57.816210168909286]
  We leverage recent progress on textual entailment models to address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.
  arXiv  Detail & Related papers  (2023-05-31T21:04:04Z)
• PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition [63.51569687229681]
  We argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 45K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document.
  arXiv  Detail & Related papers  (2022-12-21T04:03:33Z)
• Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection [62.071938098215085]
  We focus on the Commongen benchmark, wherein the aim is to generate a plausible sentence for a given set of input concepts. We propose strategies for enhancing the semantic correctness of the generated text.
  arXiv  Detail & Related papers  (2020-12-19T23:23:40Z)

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.