mlsanityData to 14 Oct 2026

Concise Answers to Complex Questions: Summarization of Long-form Answers

arXiv 2305.19271 ↗First posted 30 May 2023cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Long-form question answering systems provide rich information by presenting paragraph-level answers, often containing optional background or auxiliary information. While such comprehensive answers are helpful, not all information is required to answer the question (e.g. users with domain knowledge do not need an explanation of background). Can we provide a concise version of the answer by summarizing it, while still addressing the question? We conduct a user study on summarized answers generated from state-of-the-art models and our newly proposed extract-and-decontextualize approach. We find a large proportion of long-form answers (over 90%) in the ELI5 domain can be adequately summarized by at least one system, while complex and implicit answers are challenging to compress. We observe that decontextualization improves the quality of the extractive summary, exemplifying its potential in the summarization task. To promote future work, we provide an extractive summarization dataset covering 1K long-form answers and our user study annotations. Together, we present the first study on summarizing long-form answers, taking a step forward for QA agents that can provide answers at multiple granularities.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 50 of its 58 references that are in the map. First posted on arXiv 30 May 2023.

Builds on

50 of 58 references.

References · 50

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  6. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  9. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  10. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  11. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  12. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
38 more
  1. 2019ELI5: Long Form Question Answeringcited by 575
  2. 2019Text Summarization with Pretrained Encoderscited by 556
  3. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 396
  4. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  5. 2018Generating Wikipedia by Summarizing Long Sequencescited by 335
  6. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  7. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  8. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  9. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 236
  10. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  11. 2021Hurdles to Progress in Long-form Question Answeringcited by 167
  12. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 161
  13. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  14. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  15. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  16. 2021Decontextualization: Making Sentences Stand-Alonecited by 102
  17. 2019On Extractive and Abstractive Neural Document Summarization with Transformer Language Modelscited by 83
  18. 2020Extractive Opinion Summarization in Quantized Transformer Spacescited by 76
  19. 2020Improved Natural Language Generation via Loss Truncationcited by 75
  20. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 75
  21. 2020WikiAsp: A Dataset for Multi-domain Aspect-based Summarizationcited by 56
  22. 2018A Unified Model for Extractive and Abstractive Summarization using Inconsistency Losscited by 47
  23. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  24. 2021Exploring Neural Models for Query-Focused Summarizationcited by 44
  25. 2020AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarizationcited by 42
  26. 2021ASPECTNEWS: Aspect-Oriented Summarization of News Documentscited by 37
  27. 2021Controllable Open-ended Question Generation with A New Question Type Ontologycited by 36
  28. 2016Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraintscited by 34
  29. 2022Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarizationcited by 32
  30. 2019Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answeringcited by 25
  31. 2022Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Modelcited by 20
  32. 2022How Do We Answer Complex Questions: Discourse Structure of Long-form Answerscited by 19
  33. 2022SNaC: Coherence Error Detection for Narrative Summarizationcited by 19
  34. 2021AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarizationcited by 10
  35. 2022Controlled Text Reductioncited by 10
  36. 2020Multi-hop Inference for Question-driven Summarizationcited by 7
  37. 2022Modeling Exemplification in Long-form Question Answering via Retrievalcited by 7
  38. 2020Query Focused Multi-Document Summarization with Distant Supervisioncited by 6

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 2.

7 papers.

  1. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  2. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 201
  3. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 44
  4. 2024DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generationcited by 22
  5. 2023SEMQA: Semi-Extractive Multi-Source Question Answeringcited by 19
  6. 2025Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysiscited by 3
  7. 2025A Unifying Scheme for Extractive Content Selection Taskscited by 1