# Exploration of Plan-Guided Summarization for Narrative Texts: the Case of Small Language Models

arXiv: https://arxiv.org/abs/2504.09071 · HTML: https://mlsanity.com/paper/2504.09071/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 12 Apr 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [MixQG: Neural Question Generation with Mixed Answer Types](https://mlsanity.com/paper/2110.08175/) (2021)
- [Learning to Plan and Generate Text with Citations](https://mlsanity.com/paper/2404.03381/) (2024)
- [Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization](https://mlsanity.com/paper/2212.10449/) (2022)
- [Generating EDU Extracts for Plan-Guided Summary Re-Ranking](https://mlsanity.com/paper/2305.17779/) (2023)
- [Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection](https://mlsanity.com/paper/2111.07935/) (2021)
- [Analysis of Plan-based Retrieval for Grounded Text Generation](https://mlsanity.com/paper/2408.10490/) (2024)
- [Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2402.02077/) (2024)

## Built on by (most cited first, 1 of 1)

- [Enhancing Long Document Long Form Summarisation with Self-Planning](https://mlsanity.com/paper/2512.17179/) (2025)

## Abstract (arXiv)

Plan-guided summarization attempts to reduce hallucinations in small language models (SLMs) by grounding generated summaries to the source text, typically by targeting fine-grained details such as dates or named entities. In this work, we investigate whether plan-based approaches in SLMs improve summarization in long document, narrative tasks. Narrative texts' length and complexity often mean they are difficult to summarize faithfully. We analyze existing plan-guided solutions targeting fine-grained details, and also propose our own higher-level, narrative-based plan formulation. Our results show that neither approach significantly improves on a baseline without planning in either summary quality or faithfulness. Human evaluation reveals that while plan-guided approaches are often well grounded to their plan, plans are equally likely to contain hallucinations compared to summaries. As a result, the plan-guided summaries are just as unfaithful as those from models without planning. Our work serves as a cautionary tale to plan-guided approaches to summarization, especially for long, complex domains such as narrative texts. Code available at https://github.com/amazon-science/plan-guided-summarization