arXiv subjects

Lydia B. Chilton

Publications and source records attributed to Lydia B. Chilton.

33 records · Page 2Linked to original sources

arXiv2024

Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers

We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors to ensure that the stories have not been shared online (and therefore are unseen by the models), and to obtain informed evaluations of summary quality using judgments from the authors themselves. Through quantitative and qualitative analysis grounded in narrative theory, we compare GPT-4, Claude-2.1, and LLama-2-70B. We find that all three models make faithfulness mistakes in over 50% of summaries and struggle with specificity and interpretation of difficult subtext. We additionally demonstrate that LLM ratings and other automatic metrics for summary quality do not correlate well with the quality ratings from the writers.

cs.CL↗

arXiv2024

DIDUP: Dynamic Iterative Development for UI Prototyping

Large language models (LLMs) are remarkably good at writing code. A particularly valuable case of human-LLM collaboration is code-based UI prototyping, a method for creating interactive prototypes that allows users to view and fully engage with a user interface. We conduct a formative study of GPT Pilot, a leading LLM-generated code-prototyping system, and find that its inflexibility towards change once development has started leads to weaknesses in failure prevention and dynamic planning; it closely resembles the linear workflow of the waterfall model. We introduce DIDUP, a system for code-based UI prototyping that follows an iterative spiral model, which takes changes and iterations that come up during the development process into account. We propose three novel mechanisms for LLM-generated code-prototyping systems: (1) adaptive planning, where plans should be dynamic and reflect changes during implementation, (2) code injection, where the system should write a minimal amount of code and inject it instead of rewriting code so users have a better mental model of the code evolution, and (3) lightweight state management, a simplified version of source control so users can quickly revert to different working states. Together, this enables users to rapidly develop and iterate on prototypes.

cs.HC↗

arXiv2024

Scrolly2Reel: Retargeting Graphics for Social Media Using Narrative Beats

Content retargeting is crucial for social media creators. Once great content is created, it is important to reach as broad an audience as possible. This is particularly important in journalism where younger audiences are shifting away from print and towards short-video platforms. Many newspapers already create rich graphics for the web that they want to be able to reuse for social media. One example is scrollytelling sequences or "scrollies" -- immersive articles with graphics like animation, charts, and 3D visualizations that appear as a user scrolls. We present a system that helps transform scrollies into social media videos. By using the scriptwriting concept of narrative beats to extract fundamental storytelling units, we can create videos that are more aligned with narration, and allow for better pacing and stylistic changes. Narrative beats are thus an important primitive to retargeting content that matches the style of a new medium while maintaining the cohesiveness of the original content.

cs.HC↗

arXiv2024

Eliciting Topic Hierarchies from Large Language Models

Current research has explored how Generative AI can support the brainstorming process for content creators, but a gap remains in exploring support-tools for the pre-writing process. Specifically, our research is focused on supporting users in finding topics at the right level of specificity for their audience. This process is called topic scoping. Topic scoping is a cognitively demanding task, requiring users to actively recall subtopics in a given domain. This manual approach also reduces the diversity of subtopics that a user is able to explore. We propose using Large Language Models (LLMs) to support the process of topic scoping by iteratively generating subtopics at increasing levels of specificity: dynamically creating topic hierarchies. We tested three different prompting strategies and found that increasing the amount of context included in the prompt improves subtopic generation by 20 percentage points. Finally, we discuss applications of this research in education, content creation, and product management.

cs.HC↗

arXiv2024

Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflow

Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable lure of AI, it is uncertain how useful generative AI workflows are after the novelty wears off. Additionally, workflows built with generative AI have the potential to be easily customized to fit users' individual needs, but do users take advantage of this? We conducted a three-week longitudinal study with 12 users to understand the familiarization and customization of generative AI tools for science communication. Our study revealed that there exists a familiarization phase, during which users were exploring the novel capabilities of the workflow and discovering which aspects they found useful. After this phase, users understood the workflow and were able to anticipate the outputs. Surprisingly, after familiarization the perceived utility of the system was rated higher than before, indicating that the perceived utility of AI is not just a novelty effect. The increase in benefits mainly comes from end-users' ability to customize prompts, and thus potentially appropriate the system to their own needs. This points to a future where generative AI systems can allow us to design for appropriation.

cs.HC↗

arXiv2024

PodReels: Human-AI Co-Creation of Video Podcast Teasers

Video podcast teasers are short videos that can be shared on social media platforms to capture interest in the full episodes of a video podcast. These teasers enable long-form podcasters to reach new audiences and gain new followers. However, creating a compelling teaser from an hour-long episode is challenging. Selecting interesting clips requires significant mental effort; editing the chosen clips into a cohesive, well-produced teaser is time-consuming. To support the creation of video podcast teasers, we first investigate what makes a good teaser. We combine insights from both audience comments and creator interviews to determine a set of essential ingredients. We also identify a common workflow shared by creators during the process. Based on these findings, we introduce a human-AI co-creative tool called PodReels to assist video podcasters in creating teasers. Our user study shows that PodReels significantly reduces creators' mental demand and improves their efficiency in producing video podcast teasers.

cs.HC↗

arXiv2024

ReelFramer: Human-AI Co-Creation for News-to-Video Translation

Short videos on social media are the dominant way young people consume content. News outlets aim to reach audiences through news reels -- short videos conveying news -- but struggle to translate traditional journalistic formats into short, entertaining videos. To translate news into social media reels, we support journalists in reframing the narrative. In literature, narrative framing is a high-level structure that shapes the overall presentation of a story. We identified three narrative framings for reels that adapt social media norms but preserve news value, each with a different balance of information and entertainment. We introduce ReelFramer, a human-AI co-creative system that helps journalists translate print articles into scripts and storyboards. ReelFramer supports exploring multiple narrative framings to find one appropriate to the story. AI suggests foundational narrative details, including characters, plot, setting, and key information. ReelFramer also supports visual framing; AI suggests character and visual detail designs before generating a full storyboard. Our studies show that narrative framing introduces the necessary diversity to translate various articles into reels, and establishing foundational details helps generate scripts that are more relevant and coherent. We also discuss the benefits of using narrative framing and foundational details in content retargeting.

cs.HC↗

arXiv2023

Tweetorial Hooks: Generative AI Tools to Motivate Science on Social Media

Communicating science and technology is essential for the public to understand and engage in a rapidly changing world. Tweetorials are an emerging phenomenon where experts explain STEM topics on social media in creative and engaging ways. However, STEM experts struggle to write an engaging "hook" in the first tweet that captures the reader's attention. We propose methods to use large language models (LLMs) to help users scaffold their process of writing a relatable hook for complex scientific topics. We demonstrate that LLMs can help writers find everyday experiences that are relatable and interesting to the public, avoid jargon, and spark curiosity. Our evaluation shows that the system reduces cognitive load and helps people write better hooks. Lastly, we discuss the importance of interactivity with LLMs to preserve the correctness, effectiveness, and authenticity of the writing.

cs.HC↗

arXiv2023

Design Guidelines for Prompt Engineering Text-to-Image Generative Models

Text-to-image generative models are a new and powerful way to generate visual artwork. However, the open-ended nature of text as interaction is double-edged; while users can input anything and have access to an infinite range of generations, they also must engage in brute-force trial and error with the text prompt when the result quality is poor. We conduct a study exploring what prompt keywords and model hyperparameters can help produce coherent outputs. In particular, we study prompts structured to include subject and style keywords and investigate success and failure modes of these prompts. Our evaluation of 5493 generations over the course of five experiments spans 51 abstract and concrete subjects as well as 51 abstract and figurative styles. From this evaluation, we present design guidelines that can help people produce better outcomes from text-to-image generative models.

cs.HC↗

arXiv2023

Challenges and Opportunities for the Design of Smart Speakers

Advances in voice technology and voice user interfaces (VUIs) -- such as Alexa, Siri, and Google Home -- have opened up the potential for many new types of interaction. However, despite the potential of these devices reflected by the growing market and body of VUI research, there is a lingering sense that the technology is still underused. In this paper, we conducted a systematic literature review of 35 papers to identify and synthesize 127 VUI design guidelines into five themes. Additionally, we conducted semi-structured interviews with 15 smart speaker users to understand their use and non-use of the technology. From the interviews, we distill four design challenges that contribute the most to non-use. Based on their (non-)use, we identify four opportunity spaces for designers to explore such as focusing on information support while multitasking (cooking, driving, childcare, etc), incorporating users' mental models for smart speakers, and integrating calm design principles.

cs.HC↗

arXiv2023

PopBlends: Strategies for Conceptual Blending with Large Language Models

Pop culture is an important aspect of communication. On social media people often post pop culture reference images that connect an event, product or other entity to a pop culture domain. Creating these images is a creative challenge that requires finding a conceptual connection between the users' topic and a pop culture domain. In cognitive theory, this task is called conceptual blending. We present a system called PopBlends that automatically suggests conceptual blends. The system explores three approaches that involve both traditional knowledge extraction methods and large language models. Our annotation study shows that all three methods provide connections with similar accuracy, but with very different characteristics. Our user study shows that people found twice as many blend suggestions as they did without the system, and with half the mental demand. We discuss the advantages of combining large language models with knowledge bases for supporting divergent and convergent thinking.

cs.HC↗

arXiv2022

How Much is Performance Worth to Users? A Quantitative Approach

Architects and systems designers artfully balance multiple competing design constraints during the design process but are unable to translate between system metrics and end user experience. This work presents three methodologies to fill in this gap. The first is an incentive-compatible methodology that determines a "ground truth" measurement of users' value of speed in terms of US dollars, and find that users would accept a performance losses of 10%, 20%, and 30% to their personal computer in exchange for \$2.27, \$4.07, and \$4.43 per day, respectively. However, while highly accurate the methodology is a painstaking process and does not scale with large numbers of participants. To allow for scalability, we introduce a second methodology -- a lab-based simulation experiment -- which finds that users would accept a permanent performance loss of 10%, 20%, and 30% to their personal computer in exchange for \$127, \$169, and \$823, respectively. Finally, to allow for even greater scalability, we introduce a third methodology -- a survey -- and observe that the lack of incentive compatibility and the lack of hands-on experience with throttled device performance skews the results significantly, thus demonstrating the need for lab-based or incentive compatible study designs. By quantifying the tradeoff between user satisfaction and performance, we enable architects and systems designers to make more nuanced tradeoffs between design requirements.

cs.HC↗

arXiv2021

Eliciting Gestures for Novel Note-taking Interactions

Handwriting recognition is improving in leaps and bounds, and this opens up new opportunities for stylus-based interactions. In particular, note-taking applications can become a more intelligent user interface, incorporating new features like autocomplete and integrated search. In this work we ran a gesture elicitation study, asking 21 participants to imagine how they would interact with an imaginary, intelligent note-taking application. We report agreement on the elicited gestures, finding that while existing common interactions are prevalent (like double taps and long presses) a number of more novel interactions (like dragging selected items to hotspots or using annotations) were also well-represented. We discuss the mental models participants drew on when explaining their gestures and what kind of feedback users might need to move to more stylus-centric interactions.

cs.HC↗

arXiv2021

Sparks: Inspiration for Science Writing using Language Models

Large-scale language models are rapidly improving, performing well on a wide variety of tasks with little to no customization. In this work we investigate how language models can support science writing, a challenging writing task that is both open-ended and highly constrained. We present a system for generating "sparks", sentences related to a scientific concept intended to inspire writers. We find that our sparks are more coherent and diverse than a competitive language model baseline, and approach a human-created gold standard. In a study with 13 PhD students writing on topics of their own selection, we find three main use cases of sparks: aiding with crafting detailed sentences, providing interesting angles to engage readers, and demonstrating common reader perspectives. We also report on the various reasons sparks were considered unhelpful, and discuss how we might improve language models as writing support tools.

cs.HC↗

arXiv2018

Cicero: Multi-Turn, Contextual Argumentation for Accurate Crowdsourcing

Traditional approaches for ensuring high quality crowdwork have failed to achieve high-accuracy on difficult problems. Aggregating redundant answers often fails on the hardest problems when the majority is confused. Argumentation has been shown to be effective in mitigating these drawbacks. However, existing argumentation systems only support limited interactions and show workers general justifications, not context-specific arguments targeted to their reasoning. This paper presents Cicero, a new workflow that improves crowd accuracy on difficult tasks by engaging workers in multi-turn, contextual discussions through real-time, synchronous argumentation. Our experiments show that compared to previous argumentation systems which only improve the average individual worker accuracy by 6.8 percentage points on the Relation Extraction domain, our workflow achieves 16.7 percentage point improvement. Furthermore, previous argumentation approaches don't apply to tasks with many possible answers; in contrast, Cicero works well in these cases, raising accuracy from 66.7% to 98.8% on the Codenames domain.

cs.HC↗