mlsanityData to 14 Oct 2026

Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing

arXiv 2208.00636 ↗First posted 1 Aug 2022cs.HC cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

Writing with next-phrase suggestions powered by large language models is becoming more pervasive by the day. However, research to understand writers' interaction and decision-making processes while engaging with such systems is still emerging. We conducted a qualitative study to shed light on writers' cognitive processes while writing with next-phrase suggestion systems. To do so, we recruited 14 amateur writers to write two reviews each, one without suggestions and one with suggestions. Additionally, we also positively and negatively biased the suggestion system to get a diverse range of instances where writers' opinions and the bias in the language model align or misalign to varying degrees. We found that writers interact with next-phrase suggestions in various complex ways: Writers abstracted and extracted multiple parts of the suggestions and incorporated them within their writing, even when they disagreed with the suggestion as a whole; along with evaluating the suggestions on various criteria. The suggestion system also had various effects on the writing process, such as altering the writer's usual writing plans, leading to higher levels of distraction etc. Based on our qualitative analysis using the cognitive process model of writing by Hayes as a lens, we propose a theoretical model of 'writer-suggestion interaction' for writing with GPT-2 (and causal language models in general) for a movie review writing task, followed by directions for future research and design.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 15 of its 52 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

15 of 52 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  3. 2018Model Cards for Model Reportingcited by 1,080
  4. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  5. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  6. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  7. 2019Measuring Bias in Contextualized Word Representationscited by 276
  8. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 249
  9. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 218
  10. 2017Regularizing and Optimizing LSTM Language Modelscited by 205
  11. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  12. 2019Gmail Smart Compose: Real-Time Assisted Writingcited by 98
3 more
  1. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  2. 2021The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writerscited by 61
  3. 2021Artificial intelligence in communication impacts language and social relationshipscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 5; 2026: 8.

27 papers.

Sort:

  1. 2023Does Writing with Language Models Reduce Content Diversity?cited by 192
  2. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 148
  3. 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
  4. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  5. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 60
  6. 2024Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Modelscited by 51
  7. 2023VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototypingcited by 46
  8. 2023Writer-Defined AI Personas for On-Demand Feedback Generationcited by 36
  9. 2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writerscited by 32
  10. 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wildcited by 25
  11. 2025Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Processcited by 14
  12. 2024Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Toolscited by 13
15 more
  1. 2024The Dearth of the Author in AI-Supported Writingcited by 10
  2. 2023Human-AI Interactions and Societal Pitfallscited by 9
  3. 2025CorpusStudio: Surfacing Emergent Patterns in a Corpus of Prior Work while Writingcited by 5
  4. 2026Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideascited by 4
  5. 2024CoCo Matrix: Taxonomy of Cognitive Contributions in Co-writing with Intelligent Agentscited by 2
  6. 2024When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-Writingcited by 2
  7. 2025PromptCanvas: Composable Prompting Workspaces Using Dynamic Widgets for Exploration and Iteration in Creative Writingcited by 2
  8. 2025Exploring Mobile Touch Interaction with Large Language Modelscited by 1
  9. 2026Who Owns the Text? Design Patterns for Preserving Authorship in AI-Assisted Writingcited by 1
  10. 2026What happens when reviewers receive AI feedback in their reviews?cited by 1
  11. 2026PlayWrite: A Multimodal System for AI Supported Narrative Co-Authoring Through Play in XRcited by 1
  12. 2026User Review Writing via Interview with Dialogue Systemscited by 1
  13. 2026Designing Proactive Thought Partners for Writingcited by 1
  14. 2026Beyond Compliance: How AI Could Help Creative Writers by Refusing Themcited by 0
  15. 2026Towards Cognitive Process-Aware Proactive Writing Supportcited by 0