Elamur Research⌕
☰
home / papers / 2025 / Explanatory Summarization with Discourse-Driven Planning

Explanatory Summarization with Discourse-Driven Planning

Paper · 2025 · Dongqi Liu, Xi Yu, Vera Demberg et al.

Summary

Lay summaries of scientific papers rely heavily on explanations such as analogies, background and causal links. Standard end-to-end summarizers do not model explanations, so their outputs contain fewer of them than human-written versions. The authors propose a new task, explanatory summarization, whose goal is to produce lay summaries in which the amount and kind of explanation can be controlled.

To build training plans without manual annotation, they first parse reference summaries with the RST parser DMRST. This identifies explanatory EDUs and the target EDUs they clarify. GPT-4o then rewrites each explanation as the implicit question it answers, an idea drawn from Question Under Discussion. The resulting plan is a sequence of unanswered questions. Using Mistral as the backbone, they compare two ways of injecting the plan: in the input (Plan-Input) or as a prefix of the output (Plan-Output).

On three lay summarization corpora, both variants beat vanilla fine-tuning and previous state-of-the-art systems. They also hallucinate less and give some control over explanations. This matters because it makes generated science communication clearer and more faithful.

Key points

  • Explanations are common in lay summaries. DMRST analysis shows that explanations make up about 19.02% (eLife) and 18.19% (PLOS) of lay-summary sentences. This is roughly three times the rate in expert summaries (6.28% / 5.06%) and close to four times the rate in source papers (5.16% / 4.76%).
  • Datasets: eLife, PLOS and SciNews.
  • Baselines: Mistral FT, Blueprint MT (question-answer plans) and zero-shot GPT-4o.
  • GPT-4o as an evaluator: Its judgments agreed substantially with human raters, for example κ = 0.597 on Explanation Accuracy. This justified extending GPT-4o evaluation to the full test sets, where Plan-Input scored above Blueprint MT and Mistral FT. Human references still ranked best.
  • Qualitative case studies: These covered the cerebellum and the Musashi-1 protein. Plan-based models kept causal relations intact, whereas GPT-4o and Mistral FT overgeneralized or invented causal links. Plan-based models still occasionally misattributed facts.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of EdinburghEdinburgh · United Kingdom359 works · 77,352 citations🎓Saarland UniversitySaarbrücken · Germany148 works · 18,287 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Discourse analysis · 466 worksSummarization · 232 works

Cite

Cite as Dongqi Liu, Xi Yu, Vera Demberg and Mirella Lapata. 2025. Explanatory Summarization with Discourse-Driven Planning. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl.a.30

@article{liu2025explanatory,
  title = {{Explanatory Summarization with Discourse-Driven Planning}},
  author = {Dongqi Liu, Xi Yu, Vera Demberg and Mirella Lapata},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2025},
  doi = {10.1162/tacl.a.30},
  url = {https://doi.org/10.1162/tacl.a.30}
}

References

65 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Jake Berdi… find
  2. Tal August, Lucy Lu Wang, Jonathan Bragg, Marti A. Hearst, Andrew Head, and Kyle Lo. 2023. Paper plain: Making medical research papers approachable to healthcare consumers with natural language processing. ACM Transactions on Computer-Human Interaction, 30(5):1–38. https://doi.org/10.1145/3589955 — [doi:10.1145/3589955](https://doi.org/10.1145/3589955) ↗
  3. David I. Beaver, Craige Roberts, Mandy Simons, and Judith Tonhauser. 2017. Questions under discussion: Where information structure meets projective content. Annual Review of Linguistics, 3(Volume 3, 2017):265–284. https://doi.org/10.1146/annurev-linguistics -011516-033952 — [doi:10.1146/annurev-linguistics](https://doi.org/10.1146/annurev-linguistics) ↗
  4. Anton Benz and Katja Jasinskaja. 2017. Questions under discussion: From sentence to discourse. Discourse Processes, 54(3):177–186. https://doi.org/10.1080/0163853X .2017.1316038 — [doi:10.1080/0163853x](https://doi.org/10.1080/0163853x) ↗
  5. Meng Cao, Yue Dong, and Jackie Cheung. 2022. Hallucinated but factual! Inspecting the factuality of hallucinations in abstractive summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3340–3354, Dublin, Ireland. Assoc…
  6. Muthu Kumar Chandrasekaran, Guy Feigenblat, Eduard Hovy, Abhilasha Ravichander, Michal Shmueli-Scheuer, and Anita de Waard. 2020. Overview and insights from the shared tasks at scholarly document processing 2020: CL-SciSumm, LaySumm and LongSumm. In Proceedings of the First Workshop on Scholarly Doc… find
  7. Jiaao Chen and Diyi Yang. 2021. Structure-aware abstractive conversation summarization via discourse and action graphs. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1380–1391, Online. Associat…
  8. Felipe Costa, Sixun Ouyang, Peter Dolog, and Aonghus Lawlor. 2018. Automatic generation of natural language explanations. In Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces, pages 1–2. https://doi.org/10.1145/3180308.3180366 ↗
  9. Aldan Creo, Manuel Lama, and Juan C. Vidal. 2023. Prompting llms with content plans to enhance the summarization of scientific articles. find
  10. Kordula De Kuthy, Madeeswaran Kannan, Haemanth Santhi Ponnusamy, and Detmar Meurers. 2020. Towards automatically generating questions under discussion to link information and discourse structure. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5786–5798, Barce… find
  11. Yue Dong, Andrei Mircea, and Jackie Chi Kit Cheung. 2021. Discourse-aware unsupervised summarization for long scientific documents. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1089–1102, Online. Association for Co… find
  12. Raymond Fok, Joseph Chee Chang, Tal August, Amy X. Zhang, and Daniel S. Weld. 2024. Qlarify: Recursively expandable abstracts for dynamic information retrieval over scientific papers. In Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology, UIST ’24, New York, NY, U… find
  13. Tomas Goldsack, Zhihao Zhang, Chenghua Lin, and Carolina Scarton. 2022. Making science simple: Corpora for the lay summarisation of scientific literature. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10589–10604, Abu Dhabi, United Arab Emirates. As…
  14. Tomas Goldsack, Zhihao Zhang, Chen Tang, Carolina Scarton, and Chenghua Lin. 2023. Enhancing biomedical lay summarisation with external knowledge graphs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8016–8032, Singapore. Association for Computation… find
  15. Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, and Nguyen Cam-Tu. 2023. Diversify question generation with retrieval-augmented style transfer. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1677–1690, Singapore. find
  16. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.104 ↗
  17. Malta. Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.eacl-long.131 ↗
  18. Bin Guo, Hao Wang, Yasan Ding, Wei Wu, Shaoyang Hao, Yueqi Sun, and Zhiwen Yu. 2021a. Conditional text generation for harmonious human-machine interaction. ACM Transactions on Intelligent Systems and Technology (TIST), 12(2):1–50. https://doi.org/10.1145/3439816 — [doi:10.1145/3439816](https://doi.org/10.1145/3439816) ↗
  19. Fantine Huot, Joshua Maynez, Shashi Narayan, Reinald Kim Amplayo, Kuzman Ganchev, Annie Priyadarshini Louis, Anders Sandholm, Dipanjan Das, and Mirella Lapata. 2023. Text-blueprint: An interactive platform for plan-based conditional generation. In Proceedings of the 17th Conference of the European C… find
  20. Yue Guo, Wei Qiu, Yizhong Wang, and Trevor Cohen. 2021b. Automated lay language summarization of biomedical scientific reviews. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1):160–168. https://doi.org/10.1609/aaai.v35i1.16089 — [doi:10.1609/aaai.v35i1.16089](https://doi.org/10.1609/aaai.v35i1.16089) ↗
  21. Grigorii Guz and Giuseppe Carenini. 2020. Coreference for discourse parsing: A neural approach. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 160–167, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.codi-1.17 ↗
  22. HyoJung Han, Jordan Boyd-Graber, and Marine Carpuat. 2023. Bridging background knowledge gaps in translation with automatic explicitation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9718–9735, Singapore. Association for Computational Linguistics.…
  23. Freya Hewett, Hadi Asghari, and Manfred Stede. 2024. Elaborative simplification for German-language texts. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 29–39, Kyoto, Japan. Association for Computational Linguistics. https://doi.org/10 .1865… find
  24. Fantine Huot, Joshua Maynez, Chris Alberti, Reinald Kim Amplayo, Priyanka Agrawal, Constanza Fierro, Shashi Narayan, and Mirella Lapata. 2024. μ PLAN: Summarizing using a content plan as cross-lingual bridge. In Proceedings of the 18th Conference of the European Chapter of the Association for Comput… find
  25. Dongwhan Kim and Joonhwan Lee. 2019. Designing an algorithm-driven text generation system for personalized and interactive news reading. International Journal of Human–Computer Interaction, 35(2):109–122. https://doi.org/10.1080/10447318 .2018.1437864 — [doi:10.1080/10447318](https://doi.org/10.1080/10447318) ↗
  26. J. Peter Kincaid, Robert P. Fishburne Jr, Richard L. Rogers, and Brad S. Chissom. 1975. Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel. https://doi.org/10.21236/ADA006655 — [doi:10.21236/ada006655](https://doi.org/10.21236/ada006655) ↗
  27. Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, and Junyi Jessy Li. 2023. Discourse analysis via questions and answers: Parsing dependency structures of questions under discussion. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11181–11195, Toron…
  28. Philippe Laban, Tobias Schnabel, Paul N. Bennett, and Marti A. Hearst. 2022. SummaC: Re-visiting NLI-based models for inconsistency detection in summarization. Transactions of the Association for Computational Linguistics, 10:163–177. https://doi.org/10 .1162/tacl_a_00453 find
  29. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
  30. Dongqi Liu and Vera Demberg. 2023. ChatGPT vs human-authored text: Insights into controllable text summarization and sentence style transfer. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 1–18, Toronto, Canada.…
  31. Dongqi Liu and Vera Demberg. 2024. RST-LoRA: A discourse-aware low-rank adaptation for long document abstractive summarization. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), p… find
  32. Dongqi Liu, Xudong Hong, Pin-Jie Lin, Ernie Chang, and Vera Demberg. 2022. Two-stage movie script summarization: An efficient method for low-resource long document summarization. In Proceedings of the Workshop on Automatic Summarization for Creative Writing, pages 57–66, Gyeongju, Republic of Korea.… find
  33. Dongqi Liu, Yifan Wang, and Vera Demberg. 2023. Incorporating distributions of discourse structure for long document abstractive summarization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5574–5590, Toronto, Canada. Associ… find
  34. Dongqi Liu, Yifan Wang, Jia Loy, and Vera Demberg. 2024. SciNews: From scholarly complexities to public narratives – a dataset for scientific news report generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING… find
  35. Dongqi Liu, Chenxi Whitehouse, Xi Yu, Louis Mahon, Rohit Saxena, Zheng Zhao, Yifu Qiu, Mirella Lapata, and Vera Demberg. 2025. What is that talk about? A video-to-text summarization dataset for scientific presentations.
  36. Zhengyuan Liu and Nancy Chen. 2021. Controllable neural dialogue summarization with personal named entity planning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 92–106, Online and Punta Cana, Dominican Republic. Association for Computational Lingui… find
  37. Zhengyuan Liu, Ke Shi, and Nancy Chen. 2020. Multilingual neural RST discourse parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6730–6738, Barcelona, Spain (Online). International Committee on Computational Linguistics. https://doi.org/10 .18653/v1/202…
  38. Zhengyuan Liu, Ke Shi, and Nancy Chen. 2021. DMRST: A joint framework for document-level multilingual RST discourse segmentation and parsing. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 154–164, Punta Cana, Dominican Republic and Online. Association for Computa… find
  39. Adian Liusie, Potsawee Manakul, and Mark Gales. 2024. LLM comparative assessment: Zero-shot NLG evaluation through pairwise comparisons using large language models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers),…
  40. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations. find
  41. Annie Louis, Aravind Joshi, and Ani Nenkova. 2010. Discourse indicators for content selection in summarization. In Proceedings of the SIGDIAL 2010 Conference, pages 147–156, Tokyo, Japan. Association for Computational Linguistics. find
  42. Shashi Narayan, Joshua Maynez, Reinald Kim Amplayo, Kuzman Ganchev, Annie Louis, Fantine Huot, Anders Sandholm, Dipanjan Das, and Mirella Lapata. 2023. Conditional generation with a question-answering blueprint. Transactions of the Association for Computational Linguistics, 11:974–996. https://doi.… ↗
  43. Zheheng Luo, Qianqian Xie, and Sophia Ananiadou. 2022. Readability controllable biomedical document summarization. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4667–4680, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  44. Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simões, Vitaly Nikolaev, and Ryan McDonald. 2021. Planning with learned entity prompts for abstractive summarization. Transactions of the Association for Computational Linguistics, 9:1475–1492. https://doi.org/10.1162/tacl a 00438 ↗
  45. Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, and Manabu Okumura. 2024. Can we obtain significant success in RST discourse parsing by using large language models? In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers),…
  46. William C. Mann and Sandra A. Thompson. 1987. Rhetorical Structure Theory: A Theory of Text Organization. University of Southern California, Information Sciences Institute Los Angeles. find
  47. Daniel Marcu. 1997. From discourse structures to text summaries. In Intelligent Scalable Text Summarization. find
  48. Daniel Marcu. 1999. Discourse trees are good indicators of importance in text. Advances in Automatic Text Summarization, 293:123–136. find
  49. Daniel Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press. https://doi.org/10.7551/mitpress/6754.001.0001 ↗
  50. Amit Moryossef, Mathias Müller, Anne Göhring, Zifan Jiang, Yoav Goldberg, and Sarah Ebling. 2023. An open-source gloss-based baseline for spoken to signed language translation. In Proceedings of the Second International Workshop on Automatic Translation for Signed and Spoken Languages, pages 22–33… find
  51. Annishka Oksa, Slava Kalyuga, and Paul Chandler. 2010. Expertise reversal effect in using explanatory notes for readers of shakespearean text. Instructional Science, 38:217–236. https://doi.org/10.1007/s11251-009-9109-6 ↗
  52. Ratish Puduppully, Li Dong, and Mirella Lapata. 2019. Data-to-text generation with content selection and planning. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):6908–6915. https://doi.org/10 .1609/aaai.v33i01.33016908 find
  53. Craige Roberts. 2012. Information structure: Towards an integrated formal theory of pragmatics. Semantics and Pragmatics, 5:6–1. https://doi.org/10.3765/sp.5.6 ↗
  54. Yixiao Song, Yekyung Kim, and Mohit Iyyer. 2024. VeriScore: Evaluating the factuality of verifiable claims in long-form text generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9447–9474, Miami, Florida, USA. Association for Computational Linguistics. https://…
  55. Neha Srikanth and Junyi Jessy Li. 2021. Elaborative simplification: Content addition and explanation generation in text simplification. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5123–5137, Online. Association for Computational Linguistics. https://doi.org /… ↗
  56. Manfred Stede, Maite Taboada, and Debopam Das. 2017. Annotation guidelines for rhetorical structure. Manuscript. University of Potsdam and Simon Fraser University. find
  57. Computational Linguistics, pages 5021–5031, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.451 — [doi:10.18653/v1](https://doi.org/10.18653/v1) ↗
  58. Renliang Sun, Hanqi Jin, and Xiaojun Wan. 2021. Document-level text simplification: Dataset, criteria and baseline. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7997–8013, Online and Punta Cana, Dominican Republic. Association for Computational Lin… find
  59. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26–30, 2020. find
  60. Chen Tang, Shun Wang, Tomas Goldsack, and Chenghua Lin. 2023. Improving biomedical abstractive summarisation with knowledge aggregation from citation papers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 606–618, Singapore. Association for Computati… find
  61. Haining Wang, Jason Clark, Hannah McKelvey, Leila Sterman, Zheng Gao, Zuoyu Tian, Sandra Kübler, and Xiaozhong Liu. 2025. Science out of its ivory tower: Improving accessibility with reinforcement learning. https://doi.org/10.47989/ir30iConf47530 — [doi:10.47989/ir30iconf47530](https://doi.org/10.47989/ir30iconf47530) ↗
  62. Yating Wu, Ritika Mangla, Greg Durrett, and Junyi Jessy Li. 2023a. QUDeval: The evaluation of questions under discussion discourse parsing. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5344–5363, Singapore. Association for Computational Linguistics…
  63. Yating Wu, William Sheffield, Kyle Mahowald, and Junyi Jessy Li. 2023b. Elaborative simplification as implicit questions under discussion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5525–5537, Singapore. Association for Computational Linguistics.…
  64. Jiacheng Xu, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Discourse-aware neural extractive text summarization. In Proceedings of the 58th Annual Meeting of the Association for Zhihao Zhang, Tomas Goldsack, Carolina Scarton, and Chenghua Lin. 2024. ATLAS: Improving lay summarisation with attribute-bas…
  65. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Thirty-seventh Conference on Neural Information Processing…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2025-explanatory-summarization-discourse-driven-planning/