# Contrastive Learning with Narrative Twins for Modeling Story Salience

arXiv: https://arxiv.org/abs/2601.07765 · HTML: https://mlsanity.com/paper/2601.07765/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders](https://mlsanity.com/paper/2104.08027/) (2021)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [Exploring Content Selection in Summarization of Novel Chapters](https://mlsanity.com/paper/2005.01840/) (2020)
- [Negative Sampling for Contrastive Representation Learning: A Review](https://mlsanity.com/paper/2206.00212/) (2022)
- [Movie Summarization via Sparse Graph Construction](https://mlsanity.com/paper/2012.07536/) (2020)
- [Automatic Event Salience Identification](https://mlsanity.com/paper/1809.00647/) (2018)
- [Salience-Aware Event Chain Modeling for Narrative Understanding](https://mlsanity.com/paper/2109.10475/) (2021)
- [Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings](https://mlsanity.com/paper/2505.24782/) (2025)
- [Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories](https://mlsanity.com/paper/2109.03754/) (2021)
- [Select and Summarize: Scene Saliency for Movie Script Summarization](https://mlsanity.com/paper/2404.03561/) (2024)
- [Modeling Event Salience in Narratives via Barthes' Cardinal Functions](https://mlsanity.com/paper/2011.01785/) (2020)

## Built on by (most cited first, 2 of 2)

- [SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning](https://mlsanity.com/paper/2604.21782/) (2026)
- [What, When, and How: Audio Description as Constrained Global Optimization](https://mlsanity.com/paper/2609.30121/) (2026)

## Abstract (arXiv)

Understanding narratives requires identifying which events are most salient for a story's progression. We present a contrastive learning framework for modeling narrative salience that learns story embeddings from narrative twins: stories that share the same plot but differ in surface form. Our model is trained to distinguish a story from both its narrative twin and a distractor with similar surface features but different plot. Using the resulting embeddings, we evaluate four narratologically motivated operations for inferring salience (deletion, shifting, disruption, and summarization). Experiments on short narratives from the ROCStories corpus and longer Wikipedia plot summaries show that contrastively learned story embeddings outperform a masked-language-model baseline, and that summarization is the most reliable operation for identifying salient sentences. If narrative twins are not available, random dropout can be used to generate the twins from a single story. Effective distractors can be obtained either by prompting LLMs or, in long-form narratives, by using different parts of the same story.