Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation
Not on the map. Why?
Abstract (arXiv)
To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e.g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation. While LLMs alone can generate satisfactory news headlines, on average, human control is needed to fix undesirable model outputs. Of the interaction methods, guiding and selecting model output added the most benefit with the lowest cost (in time and effort). Further, AI assistance did not harm participants' perception of control compared to freeform editing.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 26 of its 47 references that are in the map. First posted on arXiv 16 Oct 2023.
Builds on
26 of 47 references.
References · 26
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2020Learning to summarize from human feedbackcited by 2,588
- 2023Benchmarking Large Language Models for News Summarizationcited by 445
- 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
- 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 249
- 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
- 2022Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Modelscited by 68
- 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
- 2021Perfection Not Required? Human-AI Partnerships in Code Translationcited by 42
- 2020Generating Representative Headlines for News Storiescited by 39
- 2023Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Promptingcited by 36
14 more
- 2020AI Song Contest: Human-AI Co-Creation in Songwritingcited by 25
- 2019Visual Interaction with Deep Learning Models through Collaborative Semantic Inferencecited by 24
- 2023Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativitycited by 23
- 2019Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learningcited by 19
- 2019Self-Attentive Model for Headline Generationcited by 16
- 2022Mapping the Design Space of Human-AI Interaction in Text Summarizationcited by 15
- 2020Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generationcited by 12
- 2021GenNI: Human-AI Collaboration for Data-Backed Text Generationcited by 11
- 2015Generating News Headlines with Recurrent Neural Networkscited by 10
- 2018A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translationcited by 8
- 2020THEaiTRE: Artificial Intelligence to Write a Theatre Playcited by 7
- 2021Changing the Mind of Transformers for Topically-Controllable Language Generationcited by 7
- 2023Mapping the Design Space of Interactions in Human-AI Text Co-creation Taskscited by 6
- 2021Hone as You Read: A Practical Type of Interactive Summarizationcited by 4
Built on by
Citing papers per year: 2024: 7; 2025: 5; 2026: 2.
14 papers.
Sort:
By area:
- 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
- 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
- 2025SPHERE: An Evaluation Card for Human-AI Systemscited by 9
- 2026PrefIx: Understand and Adapt to User Preference in Human-Agent Interactioncited by 7
- 2024LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Contentcited by 6
- 2024LLeMpower: Understanding Disparities in the Control and Access of Large Language Modelscited by 5
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representationcited by 4
- 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitionscited by 3
- 2024Facilitating Opinion Diversity through Hybrid NLP Approachescited by 2
- 2025FeedQUAC: Quick Unobtrusive AI-Generated Commentarycited by 2
- 2024Multilingual Fine-Grained News Headline Hallucination Detectioncited by 0
- 2025Co-creation for Sign Language Processing and Machine Translationcited by 0
- 2026When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation16 Aug 2026
- 2026PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction6 Feb 2026
- 2025FeedQUAC: Quick Unobtrusive AI-Generated Commentary23 Apr 2025
- 2025SPHERE: An Evaluation Card for Human-AI Systems24 Mar 2025
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation21 Mar 2025
- 2025Trust in Disinformation Narratives: a Trust in the News Experiment14 Mar 2025
- 2025Co-creation for Sign Language Processing and Machine Translation3 Mar 2025
- 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models7 Dec 2024
- 2024LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content20 Oct 2024
- 2024Multilingual Fine-Grained News Headline Hallucination Detection22 Jul 2024
- 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions16 Jul 2024
- 2024Position: Towards Bidirectional Human-AI Alignment13 Jun 2024
- 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
- 2024Position: Towards Bidirectional Human-AI Alignment13 Jun 2024
- 2025SPHERE: An Evaluation Card for Human-AI Systemscited by 9
- 2024LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Contentcited by 6
- 2024LLeMpower: Understanding Disparities in the Control and Access of Large Language Modelscited by 5
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representationcited by 4
- 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitionscited by 3
- 2024Facilitating Opinion Diversity through Hybrid NLP Approachescited by 2
- 2025FeedQUAC: Quick Unobtrusive AI-Generated Commentarycited by 2
- 2024Multilingual Fine-Grained News Headline Hallucination Detectioncited by 0
- 2025Co-creation for Sign Language Processing and Machine Translationcited by 0
- 2025Trust in Disinformation Narratives: a Trust in the News Experimentcited by 0
- 2026When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generationcited by 0
- 2026When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation16 Aug 2026
- 2025FeedQUAC: Quick Unobtrusive AI-Generated Commentary23 Apr 2025
- 2025SPHERE: An Evaluation Card for Human-AI Systems24 Mar 2025
- 2025"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation21 Mar 2025
- 2025Trust in Disinformation Narratives: a Trust in the News Experiment14 Mar 2025
- 2025Co-creation for Sign Language Processing and Machine Translation3 Mar 2025
- 2024LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content20 Oct 2024
- 2024Multilingual Fine-Grained News Headline Hallucination Detection22 Jul 2024
- 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions16 Jul 2024
- 2024Facilitating Opinion Diversity through Hybrid NLP Approaches15 May 2024
- 2024LLeMpower: Understanding Disparities in the Control and Access of Large Language Models14 Apr 2024