Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting

Hai, Dang,; Goller, Sven; Lehmann, Florian; Buschek, Daniel

doi:10.1145/3544548.3580969

Cited by 19 publications

(15 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers studied how these LLM suggestions can change people's writing and found that generated texts could spark new ideas [14,18,36], lower grammatical errors [58], and increase vocabulary diversity [58], while introducing cognitive challenge of integrating generated texts into the user's writing [14,90]. Researchers also studied how specific designs of LLM, such as the number of suggestions [13] or allowing users to input instructional prompts or not [25] can impact writing. Moreover, the researchers investigated the sense of ownership of writings with AI suggestions [28].…”

Section: Usingmentioning

confidence: 99%

Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts

Kim,

Han,

Adar

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Generative AI has the potential to create a new form of interactive media: AI-bridged creative language arts (CLA), which bridge the author and audience by personalizing the author's vision to the audience's context and taste at scale. However, it is unclear what the authors' values and attitudes would be regarding AI-bridged CLA.To identify these values and attitudes, we conducted an interview study with 18 authors across eight genres (e.g., poetry, comics) by presenting speculative but realistic AI-bridged CLA scenarios. We identified three benefits derived from the dynamics between author, artifact, and audience: those that 1) authors get from the process, 2) audiences get from the artifact, and 3) authors get from the audience. We found how AI-bridged CLA would either promote or reduce these benefits, along with authors' concerns. We hope our investigation hints at how AI can provide intriguing experiences to CLA audiences while promoting authors' values. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

show abstract

Section: Usingmentioning

confidence: 99%

Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts

Kim,

Han,

Adar

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Researchers have been investigating the integration of advanced artificial intelligence technologies to support various tasks. These tasks span a wide spectrum of HCI applications, encompassing question-answering systems [35], story generation [13,15], automatic generation of visualizations [16] and personalized news recommendation [32].…”

Section: Llm-supported Designmentioning

confidence: 99%

“…Specifically, the development of Low-code LLM [10] and PromptCrafter [1] have been dedicated to capturing user intent through well-crafted text prompts and optimizing the wording of prompts. Dang et al [15] integrated a user interface (UI) for phrase suggestions and a UI for zero-shot prompt inputs into an LLM. Our approach integrates the chain-of-thought technique [55] and leverages few-shot examples [7] to enhance the prompt optimization, ultimately aiming for improved and more effective outcomes.…”

Section: Llm-supported Designmentioning

confidence: 99%

Beyond Numbers: Creating Analogies to Enhance Data Comprehension and Communication with Generative AI

Chen,

Shuai,

Zhang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Fig. 1. An example of the AnalogyMate system automatically suggests data analogy for the inputs. The system first suggests data analogies according to the input, then generates corresponding design solutions and visual representations for illustrations. Finally, we show a user-rendered version of one of the analogy designs. Unfamiliar measurements usually hinder readers from grasping the scale of the numerical data, understanding the content, and feeling engaged with the context. To enhance data comprehension and communication, we leverage analogies to bridge the gap between abstract data and familiar measurements. In this work, we first conduct semi-structured interviews with design experts to identify design problems and summarize design considerations. Then, we collect an analogy dataset of 138 cases from various online sources. Based on the collected dataset, we characterize a design space for creating data analogies. Next, we build a prototype system, AnalogyMate, that automatically suggests data analogies, their corresponding design solutions, and generated visual representations powered by generative AI. The study results show the usefulness of AnalogyMate in aiding the creation process of data analogies and the effectiveness of data analogy in enhancing data comprehension and communication.

show abstract

“…For instance, Jiang et al [24] introduced PromptMaker, a tool that combines Prefixes, Settings, and Examples to create structured prompt inputs. Similarly, Dang et al [14] developed UI variants that integrate user instructions with the standard prompting, enhancing more nuanced user-model interaction.…”

Section: Mode 2: User Interface (Ui) Uer Interface (Figurementioning

confidence: 99%

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

Gao,

Gebreegziabher,

Choo

et al. 2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

With ChatGPT's release, conversational prompting has become the most popular form of human-LLM interaction. However, its effectiveness is limited for more complex tasks involving reasoning, creativity, and iteration. Through a systematic analysis of HCI papers published since 2021, we identified four key phases in the human-LLM interaction flow-planning, facilitating, iterating, and testing-to precisely understand the dynamics of this process. Additionally, we have developed a taxonomy of four primary interaction modes: Mode 1: Standard Prompting, Mode 2: User Interface, Mode 3: Context-based, and Mode 4: Agent Facilitator. This taxonomy was further enriched using the "5W1H" guideline method, which involved a detailed examination of definitions, participant roles (Who), the phases that happened (When), human objectives and LLM abilities (What), and the mechanics of each interaction mode (How). We anticipate this taxonomy will contribute to the future design and evaluation of human-LLM interaction. CCS CONCEPTS• Human-centered computing → Natural language interfaces.

show abstract

Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting

Cited by 19 publications

References 51 publications

Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts

Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts

Beyond Numbers: Creating Analogies to Enhance Data Comprehension and Communication with Generative AI

A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

Contact Info

Product

Resources

About