mlsanityData to 7 Oct 2026

How Do We Answer Complex Questions: Discourse Structure of Long-form Answers

arXiv 2203.11048 ↗First posted 21 Mar 2022cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form answers collected from three datasets, ELI5, WebGPT and Natural Questions. Our main goal is to understand how humans organize information to craft complex answers. We develop an ontology of six sentence-level functional roles for long-form answers, and annotate 3.9k sentences in 640 answer paragraphs. Different answer collection methods manifest in different discourse structures. We further analyze model-generated answers -- finding that annotators agree less with each other when annotating model-generated answers compared to annotating human-written answers. Our annotated data enables training a strong classifier that can be used for automatic analysis. We hope our work can inspire future research on discourse-level modeling and evaluation of long-form QA systems.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 19 of its 44 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

19 of 44 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  6. 2018Datasheets for Datasetscited by 1,371
  7. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  8. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  9. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  10. 2019ELI5: Long Form Question Answeringcited by 567
  11. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  12. 2020Efficient Content-Based Sparse Attention with Routing Transformerscited by 469
7 more
  1. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  2. 2016Parsing Argumentation Structures in Persuasive Essayscited by 99
  3. 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 96
  4. 2022Read before Generate! Faithful Long Form Question Answering with Machine Readingcited by 47
  5. 2021Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answeringcited by 41
  6. 2021Controllable Open-ended Question Generation with A New Question Type Ontologycited by 36
  7. 2020Query Focused Multi-Document Summarization with Distant Supervisioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 5; 2025: 2; 2026: 3.

19 papers.

Sort:

By area:

  1. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 198
  2. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  3. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 72
  4. 2022CREPE: Open-Domain Question Answering with False Presuppositionscited by 70
  5. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  6. 2022APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversationscited by 23
  7. 2024Long-Form Answers to Visual Questions from Blind and Low Vision Peoplecited by 18
  8. 2023DisCGen: A Framework for Discourse-Informed Counterspeech Generationcited by 14
  9. 2022Modeling Exemplification in Long-form Question Answering via Retrievalcited by 7
  10. 2023Concise Answers to Complex Questions: Summarization of Long-form Answerscited by 7
  11. 2024Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherencecited by 7
  12. 2025Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answeringcited by 5
7 more
  1. 2024LFQA-E: Carefully Benchmarking Long-form QA Evaluationcited by 3
  2. 2023Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructionscited by 1
  3. 2024Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generationcited by 1
  4. 2025Zoom In Disparities in Healthcare LLM Q&Acited by 1
  5. 2026A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphscited by 0
  6. 2026Which course? Discourse! Teaching Discourse and Generation in the Era of LLMscited by 0
  7. 2026DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answeringcited by 0