Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective Accounts

• URL: http://arxiv.org/abs/2512.18041v1
• Date: Fri, 19 Dec 2025 20:14:44 GMT
• Title: Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective Accounts
• Authors: Roger A. Finger, Eduardo G. Cortes, Sandro J. Rigo, Gabriel de O. Ramos,
• Abstract summary: This paper formally defines this challenge as a new NLP task: Narrative Consolidation.<n>The central objectives are chronological integrity, completeness, and the fusion of complementary details.<n>By applying a standard algorithm to TAEG, our method functions as a version selection mechanism, choosing the most central representation of each event in its correct temporal position.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Processing overlapping narrative documents, such as legal testimonies or historical accounts, often aims not for compression but for a unified, coherent, and chronologically sound text. Standard Multi-Document Summarization (MDS), with its focus on conciseness, fails to preserve narrative flow. This paper formally defines this challenge as a new NLP task: Narrative Consolidation, where the central objectives are chronological integrity, completeness, and the fusion of complementary details. To demonstrate the critical role of temporal structure in this task, we introduce Temporal Alignment Event Graph (TAEG), a graph structure that explicitly models chronology and event alignment. By applying a standard centrality algorithm to TAEG, our method functions as a version selection mechanism, choosing the most central representation of each event in its correct temporal position. In a study on the four Biblical Gospels, this structure-focused approach guarantees perfect temporal ordering (Kendall's Tau of 1.000) by design and dramatically improves content metrics (e.g., +357.2% in ROUGE-L F1). The success of this baseline method validates the formulation of Narrative Consolidation as a relevant task and establishes that an explicit temporal backbone is a fundamental component for its resolution.

Related papers

• Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech [61.00008468914252]
  We recast paragraph segmentation as the missing structuring step and fill three gaps at the intersection of speech processing and text segmentation.<n> benchmarks focus on the underexplored speech domain, where paragraph segmentation has traditionally not been part of post-processing.<n>Second, we propose a constrained-decoding formulation that lets large language models insert paragraph breaks while preserving the original transcript.<n>Third, we show that a compact model (MiniSeg) attains state-of-the-art accuracy and, when extended hierarchically, jointly predicts chapters and paragraphs with minimal computational cost.
  arXiv  Detail & Related papers  (2025-12-30T23:29:51Z)
• Chronological Passage Assembling in RAG framework for Temporal Question Answering [12.583700669377803]
  We propose ChronoRAG, a novel RAG framework specialized for narrative texts.<n>This approach focuses on two essential aspects: refining dispersed document information into coherent and structured passages.<n>We empirically demonstrate the effectiveness of ChronoRAG through experiments on the NarrativeQA and GutenQAdataset.
  arXiv  Detail & Related papers  (2025-08-26T07:23:23Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization [0.0]
  We introduce NexusSum, a multi-agent LLM framework for narrative summarization.<n>A narrative-specific preprocessing method standardizes character dialogue and descriptive text into a unified format.<n>Our method establishes a new state-of-the-art in narrative summarization, achieving up to a 30.0% improvement in BERTScore (F1) across books, movies, and TV scripts.
  arXiv  Detail & Related papers  (2025-05-30T13:26:23Z)
• Beyond Pairwise: Global Zero-shot Temporal Graph Generation [13.362845039358584]
  Temporal relation extraction (TRE) is a fundamental task in natural language processing (NLP)<n>We propose a novel zero-shot method for TRE that generates a document's complete temporal graph in a single step.<n>We also introduce OmniTemp, a new dataset with complete annotations for all pairs of targeted events within a document.
  arXiv  Detail & Related papers  (2025-02-16T13:06:50Z)
• Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization [48.57273563299046]
  We propose the task of Stepwise Summarization, which aims to generate a new appended summary each time a new document is proposed. The appended summary should not only summarize the newly added content but also be coherent with the previous summary. We show that SSG achieves state-of-the-art performance in terms of both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2024-06-08T05:37:26Z)
• The Power of Summary-Source Alignments [62.76959473193149]
  Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection. alignment of corresponding sentences between a reference summary and its source documents has been leveraged to generate training data. This paper proposes extending the summary-source alignment framework by applying it at the more fine-grained proposition span level.
  arXiv  Detail & Related papers  (2024-06-02T19:35:19Z)
• Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order [78.46986998674181]
  We propose a Unified Timeline Summarizer (UTS) that can generate abstractive and extractive timeline summaries in time order. We augment the previous Chinese large-scale timeline summarization dataset and collect a new English timeline dataset. UTS achieves state-of-the-art performance in terms of both automatic and human evaluations.
  arXiv  Detail & Related papers  (2023-01-02T20:29:40Z)
• SNaC: Coherence Error Detection for Narrative Summarization [73.48220043216087]
  We introduce SNaC, a narrative coherence evaluation framework rooted in fine-grained annotations for long summaries. We develop a taxonomy of coherence errors in generated narrative summaries and collect span-level annotations for 6.6k sentences across 150 book and movie screenplay summaries. Our work provides the first characterization of coherence errors generated by state-of-the-art summarization models and a protocol for eliciting coherence judgments from crowd annotators.
  arXiv  Detail & Related papers  (2022-05-19T16:01:47Z)
• The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries [72.48439126769627]
  We introduce the Shmoop Corpus: a dataset of 231 stories paired with detailed multi-paragraph summaries for each individual chapter. From the corpus, we construct a set of common NLP tasks, including Cloze-form question answering and a simplified form of abstractive summarization. We believe that the unique structure of this corpus provides an important foothold towards making machine story comprehension more approachable.
  arXiv  Detail & Related papers  (2019-12-30T21:03:59Z)

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.