# Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization

arXiv: https://arxiv.org/abs/2502.06185 · HTML: https://mlsanity.com/paper/2502.06185/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 65 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 45)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2109.09209/) (2021)
- [Discourse-Aware Neural Extractive Text Summarization](https://mlsanity.com/paper/1910.14142/) (2019)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters](https://mlsanity.com/paper/2204.07447/) (2022)
- [DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing](https://mlsanity.com/paper/2110.04518/) (2021)
- [FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction](https://mlsanity.com/paper/2403.02270/) (2024)
- [HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild](https://mlsanity.com/paper/2403.04307/) (2024)
- [HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation](https://mlsanity.com/paper/2406.07070/) (2024)
- [ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining](https://mlsanity.com/paper/2209.01650/) (2022)
- [How Far are We from Robust Long Abstractive Summarization?](https://mlsanity.com/paper/2210.16732/) (2022)

## Built on by (most cited first, 8 of 8)

- [StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs](https://mlsanity.com/paper/2505.22950/) (2025)
- [Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization](https://mlsanity.com/paper/2505.15291/) (2025)
- [Stress Testing Factual Consistency Metrics for Long-Document Summarization](https://mlsanity.com/paper/2511.07689/) (2025)
- [Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization](https://mlsanity.com/paper/2604.17188/) (2026)
- [Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models](https://mlsanity.com/paper/2605.28828/) (2026)
- [A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization](https://mlsanity.com/paper/2607.10390/) (2026)
- [Averaging Bias: Human Faithfulness Annotations are not Locally Faithful](https://mlsanity.com/paper/2608.00205/) (2026)
- [Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation](https://mlsanity.com/paper/2608.29884/) (2026)

## Abstract (arXiv)

Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows improved performance on top of different model baselines over several evaluation benchmarks, covering rich domains of texts, focusing on long document summarization. This underscores the significance of incorporating discourse features in developing models for scoring summaries for long document factual inconsistency.