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

arXiv: https://arxiv.org/abs/2512.18041 · HTML: https://mlsanity.com/paper/2512.18041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [Graph-based Neural Multi-Document Summarization](https://mlsanity.com/paper/1706.06681/) (2017)
- [Temporal reasoning for timeline summarisation in social media](https://mlsanity.com/paper/2501.00152/) (2024)
- [A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2505.04461/) (2025)

## Abstract (arXiv)

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, focusing on chronological integrity, completeness, and the fusion of complementary details. We establish the resources needed to study it: a formal task definition, an evaluation paradigm, the Gospel Consolidation Language Resource -- a benchmark built from the four Biblical Gospels with 169 canonical events, cross-document alignments, and a reference consolidation -- and a suite of reference systems, ranging from timeline-agnostic heuristics to the Temporal Alignment Event Graph (TAEG). Benchmarking yields three findings. First, the explicit temporal backbone is the dominant factor: every system granted the canonical timeline raises ROUGE-L F1 from 0.206 to at least 0.81. Second, on a fusion-style reference, a simple length heuristic is remarkably strong (0.947 ROUGE-L F1), outperforming graph-based selection (0.846). Third, ablations show the discriminative signal resides in temporal edges, while intra-cluster lexical similarity is uninformative. These results establish Narrative Consolidation as a distinct task and pose an open challenge: to surpass that heuristic with a principled selection mechanism and true fusion of complementary details.