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

arXiv: https://arxiv.org/abs/2203.11048 · HTML: https://mlsanity.com/paper/2203.11048/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 21 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Read before Generate! Faithful Long Form Question Answering with Machine Reading](https://mlsanity.com/paper/2203.00343/) (2022)
- [Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering](https://mlsanity.com/paper/2101.00391/) (2021)
- [Controllable Open-ended Question Generation with A New Question Type Ontology](https://mlsanity.com/paper/2107.00152/) (2021)
- [Query Focused Multi-Document Summarization with Distant Supervision](https://mlsanity.com/paper/2004.03027/) (2020)

## Built on by (most cited first, 19 of 19)

- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [WebCPM: Interactive Web Search for Chinese Long-form Question Answering](https://mlsanity.com/paper/2305.06849/) (2023)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [CREPE: Open-Domain Question Answering with False Presuppositions](https://mlsanity.com/paper/2211.17257/) (2022)
- [PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents](https://mlsanity.com/paper/2305.14564/) (2023)
- [APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations](https://mlsanity.com/paper/2209.08207/) (2022)
- [Long-Form Answers to Visual Questions from Blind and Low Vision People](https://mlsanity.com/paper/2408.06303/) (2024)
- [DisCGen: A Framework for Discourse-Informed Counterspeech Generation](https://mlsanity.com/paper/2311.18147/) (2023)
- [Modeling Exemplification in Long-form Question Answering via Retrieval](https://mlsanity.com/paper/2205.09278/) (2022)
- [Concise Answers to Complex Questions: Summarization of Long-form Answers](https://mlsanity.com/paper/2305.19271/) (2023)
- [Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence](https://mlsanity.com/paper/2402.10175/) (2024)
- [Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering](https://mlsanity.com/paper/2506.06313/) (2025)
- [LFQA-E: Carefully Benchmarking Long-form QA Evaluation](https://mlsanity.com/paper/2410.01945/) (2024)
- [Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions](https://mlsanity.com/paper/2312.12299/) (2023)
- [Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01158/) (2024)
- [Zoom In Disparities in Healthcare LLM Q&A](https://mlsanity.com/paper/2510.17476/) (2025)
- [A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphs](https://mlsanity.com/paper/2601.04859/) (2026)
- [Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs](https://mlsanity.com/paper/2602.02878/) (2026)
- [DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering](https://mlsanity.com/paper/2604.15140/) (2026)

## 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.