# Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline

arXiv: https://arxiv.org/abs/2009.00590 · HTML: https://mlsanity.com/paper/2009.00590/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 22 of 22)

- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [A Closer Look at Claim Decomposition](https://mlsanity.com/paper/2403.11903/) (2024)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)
- [On Positional Bias of Faithfulness for Long-form Summarization](https://mlsanity.com/paper/2410.23609/) (2024)
- [Proposition-Level Clustering for Multi-Document Summarization](https://mlsanity.com/paper/2112.08770/) (2021)
- [A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization](https://mlsanity.com/paper/2303.03948/) (2023)
- [Controlled Text Reduction](https://mlsanity.com/paper/2210.13449/) (2022)
- [Select and Summarize: Scene Saliency for Movie Script Summarization](https://mlsanity.com/paper/2404.03561/) (2024)
- [How "Multi" is Multi-Document Summarization?](https://mlsanity.com/paper/2210.12688/) (2022)
- [The Power of Summary-Source Alignments](https://mlsanity.com/paper/2406.00842/) (2024)
- [USB: A Unified Summarization Benchmark Across Tasks and Domains](https://mlsanity.com/paper/2305.14296/) (2023)
- [Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges](https://mlsanity.com/paper/2406.06938/) (2024)
- [SumREN: Summarizing Reported Speech about Events in News](https://mlsanity.com/paper/2212.01146/) (2022)
- [Learning to Rank Salient Content for Query-focused Summarization](https://mlsanity.com/paper/2411.00324/) (2024)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization](https://mlsanity.com/paper/2606.23989/) (2026)
- [Automatically Evaluating Opinion Prevalence in Opinion Summarization](https://mlsanity.com/paper/2307.14305/) (2023)
- [Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans](https://mlsanity.com/paper/2310.09017/) (2023)
- [Multi-Review Fusion-in-Context](https://mlsanity.com/paper/2403.15351/) (2024)

## Abstract (arXiv)

Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task, notably for generating training data for salience detection. Despite its assessed utility, the alignment step was mostly approached with heuristic unsupervised methods, typically ROUGE-based, and was never independently optimized or evaluated. In this paper, we propose establishing summary-source alignment as an explicit task, while introducing two major novelties: (1) applying it at the more accurate proposition span level, and (2) approaching it as a supervised classification task. To that end, we created a novel training dataset for proposition-level alignment, derived automatically from available summarization evaluation data. In addition, we crowdsourced dev and test datasets, enabling model development and proper evaluation. Utilizing these data, we present a supervised proposition alignment baseline model, showing improved alignment-quality over the unsupervised approach.