Search

Among the many narratives of the transformative power of Generative AI is one that sees in the world a latent nation of programmers who need to wield nothing but intentions and natural language to render their ideas in software. In this paper, this outlook is problematised in two ways. First, it is observed that generative AI is not a neutral vehicle of intention. Multiple recent studies paint a picture of the "mechanised convergence" phenomenon, namely, that generative AI has a homogenising effect on intention. Second, it is observed that the formation of intention itself is immensely challenging. Constraints, materiality, and resistance can offer paths to design metaphors for intentional tools. Finally, existentialist approaches to intention are discussed and possible implications for programming are proposed in the form of a speculative, illustrative set of intentional programming practices., Comment: Proceedings of the 35th Annual Conference of the Psychology of Programming Interest Group (PPIG 2024)

LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback), state-of-the-art LLMs like GPT4 and Llama3 are expected to have strong alignment with human preferences when prompted for a quality judgement, such as the coherence of a text. While this seems beneficial, it is not clear whether the assessments by an LLM-as-a-judge constitute only an evaluation based on the instructions in the prompts, or reflect its preference for high-quality data similar to its fine-tune data. To investigate how much influence prompting the LLMs-as-a-judge has on the alignment of AI judgements to human judgements, we analyze prompts with increasing levels of instructions about the target quality of an evaluation, for several LLMs-as-a-judge. Further, we compare to a prompt-free method using model perplexity as a quality measure instead. We aggregate a taxonomy of quality criteria commonly used across state-of-the-art evaluations with LLMs and provide this as a rigorous benchmark of models as judges. Overall, we show that the LLMs-as-a-judge benefit only little from highly detailed instructions in prompts and that perplexity can sometimes align better with human judgements than prompting, especially on textual quality.

Informal Knowledge Sharing (KS) is vital for end-user programmers to gain expertise. To better understand how personal (self-efficacy), social (reputational gains, trust between colleagues), and software-related (codification effort) variables influence spreadsheet KS intention, we conducted a multiple regressions analysis based on survey data from spreadsheet users (\textit{n}=100) in administrative and finance roles. We found that high levels of spreadsheet self-efficacy and a perception that sharing would result in reputational gains predicted higher KS intention, but individuals who found knowledge codification effortful showed lower KS intention. We also observed that regardless of occupation, users tended to report a lower sense of self-efficacy in their general spreadsheet proficiency, despite also reporting high self-efficacy in spreadsheet use for job-related contexts. Our findings suggest that acknowledging and designing for these social and personal variables can help avoid situations where experienced individuals refrain unnecessarily from sharing, with implications for spreadsheet design., Comment: 8 pages

Generative AI tools can help users with many tasks. One such task is data analysis, which is notoriously challenging for non-expert end-users due to its expertise requirements, and where AI holds much potential, such as finding relevant data sources, proposing analysis strategies, and writing analysis code. To understand how data analysis workflows can be assisted or impaired by generative AI, we conducted a study (n=15) using Bing Chat via participatory prompting. Participatory prompting is a recently developed methodology in which users and researchers reflect together on tasks through co-engagement with generative AI. In this paper we demonstrate the value of the participatory prompting method. We found that generative AI benefits the information foraging and sensemaking loops of data analysis in specific ways, but also introduces its own barriers and challenges, arising from the difficulties of query formulation, specifying context, and verifying results., Comment: Ian Drosos, Advait Sarkar, Xiaotong Xu, Carina Negreanu, Sean Rintel, and Lev Tankelevitch. 2024. "It's like a rubber duck that talks back": Understanding Generative AI-Assisted Data Analysis Workflows through a Participatory Prompting Study. In Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work (CHIWORK 2024)

LLM-powered tools like ChatGPT Data Analysis, have the potential to help users tackle the challenging task of data analysis programming, which requires expertise in data processing, programming, and statistics. However, our formative study (n=15) uncovered serious challenges in verifying AI-generated results and steering the AI (i.e., guiding the AI system to produce the desired output). We developed two contrasting approaches to address these challenges. The first (Stepwise) decomposes the problem into step-by-step subgoals with pairs of editable assumptions and code until task completion, while the second (Phasewise) decomposes the entire problem into three editable, logical phases: structured input/output assumptions, execution plan, and code. A controlled, within-subjects experiment (n=18) compared these systems against a conversational baseline. Users reported significantly greater control with the Stepwise and Phasewise systems, and found intervention, correction, and verification easier, compared to the baseline. The results suggest design guidelines and trade-offs for AI-assisted data analysis tools., Comment: Published at UIST 2024; 19 pages, 9 figures, and 2 tables

Large language models can be prompted to produce text. They can also be prompted to produce "explanations" of their output. But these are not really explanations, because they do not accurately reflect the mechanical process underlying the prediction. The illusion that they reflect the reasoning process can result in significant harms. These "explanations" can be valuable, but for promoting critical thinking rather than for understanding the model. I propose a recontextualisation of these "explanations", using the term "exoplanations" to draw attention to their exogenous nature. I discuss some implications for design and technology, such as the inclusion of appropriate guardrails and responses when models are prompted to generate explanations., Comment: In Proceedings of the ACM CHI 2024 Workshop on Human-Centered Explainable AI (HCXAI 2024)

Video tutorials are a popular medium for informal and formal learning. However, when learners attempt to view and follow along with these tutorials, they encounter what we call gaps, that is, issues that can prevent learning. We examine the gaps encountered by users of video tutorials for feature-rich software, such as spreadsheets. We develop a theory and taxonomy of such gaps, identifying how they act as barriers to learning, by collecting and analyzing 360 viewer comments from 90 Microsoft Excel video tutorials published by 43 creators across YouTube, TikTok, and Instagram. We conducted contextual interviews with 8 highly influential tutorial creators to investigate the gaps their viewers experience and how they address them. Further, we obtain insights into their creative process and frustrations when creating video tutorials. Finally, we present creators with two designs that aim to address gaps identified in the comment analysis for feedback and alternative design ideas.

Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipulating tabular data, mined from StackOverflow posts. Second, we introduce a cluster-then-select prompting technique, which adds the most representative rows from the input data to the LLM prompt. Our experiments show that LLM performance is indeed sensitive to the amount of data passed in the prompt, and that for tasks with a lot of syntactic variation in the input table, our cluster-then-select technique outperforms a random selection baseline., Comment: Paper accepted to NAACL 2024 (Findings)

Generative AI, such as image generation models and large language models, stands to provide tremendous value to end-user programmers in creative and knowledge workflows. Current research methods struggle to engage end-users in a realistic conversation that balances the actually existing capabilities of generative AI with the open-ended nature of user workflows and the many opportunities for the application of this technology. In this work-in-progress paper, we introduce participatory prompting, a method for eliciting opportunities for generative AI in end-user workflows. The participatory prompting method combines a contextual inquiry and a researcher-mediated interaction with a generative model, which helps study participants interact with a generative model without having to develop prompting strategies of their own. We discuss the ongoing development of a study whose aim will be to identify end-user programming opportunities for generative AI in data analysis workflows., Comment: Proceedings of the 34th Annual Conference of the Psychology of Programming Interest Group (PPIG 2023)

Generative AI (GenAI) systems offer unprecedented opportunities for transforming professional and personal work, yet present challenges around prompting, evaluating and relying on outputs, and optimizing workflows. We argue that metacognition$\unicode{x2013}$the psychological ability to monitor and control one's thoughts and behavior$\unicode{x2013}$offers a valuable lens to understand and design for these usability challenges. Drawing on research in psychology and cognitive science, and recent GenAI user studies, we illustrate how GenAI systems impose metacognitive demands on users, requiring a high degree of metacognitive monitoring and control. We propose these demands could be addressed by integrating metacognitive support strategies into GenAI systems, and by designing GenAI systems to reduce their metacognitive demand by targeting explainability and customizability. Metacognition offers a coherent framework for understanding the usability challenges posed by GenAI, and provides novel research and design directions to advance human-AI interaction.

The research field of end-user programming has largely been concerned with helping non-experts learn to code sufficiently well in order to achieve their tasks. Generative AI stands to obviate this entirely by allowing users to generate code from naturalistic language prompts. In this essay, we explore the extent to which "traditional" programming languages remain relevant for non-expert end-user programmers in a world with generative AI. We posit the "generative shift hypothesis": that generative AI will create qualitative and quantitative expansions in the traditional scope of end-user programming. We outline some reasons that traditional programming languages may still be relevant and useful for end-user programmers. We speculate whether each of these reasons might be fundamental and enduring, or whether they may disappear with further improvements and innovations in generative AI. Finally, we articulate a set of implications for end-user programming research, including the possibility of needing to revisit many well-established core concepts, such as Ko's learning barriers and Blackwell's attention investment model., Comment: Advait Sarkar. 2023. "Will Code Remain a Relevant User Interface for End-User Programming with Generative AI Models?" In Proceedings of the 2023 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward! '23)

Users are increasingly being warned to check AI-generated content for correctness. Still, as LLMs (and other generative models) generate more complex output, such as summaries, tables, or code, it becomes harder for the user to audit or evaluate the output for quality or correctness. Hence, we are seeing the emergence of tool-assisted experiences to help the user double-check a piece of AI-generated content. We refer to these as co-audit tools. Co-audit tools complement prompt engineering techniques: one helps the user construct the input prompt, while the other helps them check the output response. As a specific example, this paper describes recent research on co-audit tools for spreadsheet computations powered by generative models. We explain why co-audit experiences are essential for any application of generative AI where quality is important and errors are consequential (as is common in spreadsheet computations). We propose a preliminary list of principles for co-audit, and outline research challenges.

Artificial Intelligence (AI), and in particular generative models, are transformative tools for knowledge work. They problematise notions of creativity, originality, plagiarism, the attribution of credit, and copyright ownership. Critics of generative models emphasise the reliance on large amounts of training data, and view the output of these models as no more than randomised plagiarism, remix, or collage of the source data. On these grounds, many have argued for stronger regulations on the deployment, use, and attribution of the output of these models. However, these issues are not new or unique to artificial intelligence. In this position paper, using examples from literary criticism, the history of art, and copyright law, I show how creativity and originality resist definition as a notatable or information-theoretic property of an object, and instead can be seen as the property of a process, an author, or a viewer. Further alternative views hold that all creative work is essentially reuse (mostly without attribution), or that randomness itself can be creative. I suggest that creativity is ultimately defined by communities of creators and receivers, and the deemed sources of creativity in a workflow often depend on which parts of the workflow can be automated. Using examples from recent studies of AI in creative knowledge work, I suggest that AI shifts knowledge work from material production to critical integration. This position paper aims to begin a conversation around a more nuanced approach to the problems of creativity and credit assignment for generative models, one which more fully recognises the importance of the creative and curatorial voice of the users of these models and moves away from simpler notational or information-theoretic views., Comment: Advait Sarkar. 2023. Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work Beyond Mechanised Plagiarism and Stochastic Parrots. In Annual Symposium on Human-Computer Interaction for Work 2023 (CHIWORK 2023), June 13-16, 2023, Oldenburg, Germany. ACM, New York, NY, USA, 17 pages

That computers should be easy to learn and use is a rarely-questioned tenet of user interface design. But what do we gain from prioritising usability and learnability, and what do we lose? I explore how simplicity is not an inevitable truth of user interface design, but rather contingent on a series of events in the evolution of software. Not only does a rigid adherence to this doctrine place an artificial ceiling on the power and flexibility of software, but it is also culturally relative, privileging certain information cultures over others. I propose that for feature-rich software, negotiated complexity is a better target than simplicity, and we must revisit the ill-regarded relationship between learning, documentation, and software., Comment: In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (CHI EA '23)

Describing our interaction with Artificial Intelligence (AI) systems as 'collaboration' is well-intentioned, but flawed. Not only is it misleading, but it also takes away the credit of AI 'labour' from the humans behind it, and erases and obscures an often exploitative arrangement between AI producers and consumers. The AI 'collaboration' metaphor is merely the latest episode in a long history of labour appropriation and credit reassignment that disenfranchises labourers in the Global South. I propose that viewing AI as a tool or an instrument, rather than a collaborator, is more accurate, and ultimately fairer.

Fake news detection algorithms apply machine learning to various news attributes and their relationships. However, their success is usually evaluated based on how the algorithm performs on a static benchmark, independent of real users. On the other hand, studies of user trust in fake news has identified relevant factors such as the user's previous beliefs, the article format, and the source's reputation. We present a user study (n=40) evaluating how warnings issued by fake news detection algorithms affect the user's ability to detect misinformation. We find that such warnings strongly influence users' perception of the truth, that even a moderately accurate classifier can improve overall user accuracy, and that users tend to be biased towards agreeing with the algorithm, even when it is incorrect.

Code-generating large language models translate natural language into code. However, only a small portion of the infinite space of naturalistic utterances is effective at guiding code generation. For non-expert end-user programmers, learning this is the challenge of abstraction matching. We examine this challenge in the specific context of data analysis in spreadsheets, in a system that maps the users natural language query to Python code using the Codex generator, executes the code, and shows the result. We propose grounded abstraction matching, which bridges the abstraction gap by translating the code back into a systematic and predictable naturalistic utterance. In a between-subjects, think-aloud study (n=24), we compare grounded abstraction matching to an ungrounded alternative based on previously established query framing principles. We find that the grounded approach improves end-users' understanding of the scope and capabilities of the code-generating model, and the kind of language needed to use it effectively.

Large language models, such as OpenAI's codex and Deepmind's AlphaCode, can generate code to solve a variety of problems expressed in natural language. This technology has already been commercialised in at least one widely-used programming editor extension: GitHub Copilot. In this paper, we explore how programming with large language models (LLM-assisted programming) is similar to, and differs from, prior conceptualisations of programmer assistance. We draw upon publicly available experience reports of LLM-assisted programming, as well as prior usability and design studies. We find that while LLM-assisted programming shares some properties of compilation, pair programming, and programming via search and reuse, there are fundamental differences both in the technical possibilities as well as the practical experience. Thus, LLM-assisted programming ought to be viewed as a new way of programming with its own distinct properties and challenges. Finally, we draw upon observations from a user study in which non-expert end user programmers use LLM-assisted tools for solving data tasks in spreadsheets. We discuss the issues that might arise, and open research challenges, in applying large language models to end-user programming, particularly with users who have little or no programming expertise., Comment: Proceedings of the 33rd Annual Conference of the Psychology of Programming Interest Group (PPIG 2022)

Explaining the behaviour of intelligent systems will get increasingly and perhaps intractably challenging as models grow in size and complexity. We may not be able to expect an explanation for every prediction made by a brain-scale model, nor can we expect explanations to remain objective or apolitical. Our functionalist understanding of these models is of less advantage than we might assume. Models precede explanations, and can be useful even when both model and explanation are incorrect. Explainability may never win the race against complexity, but this is less problematic than it seems., Comment: Workshop on Transparency and Explanations in Smart Systems (TExSS 2022), at the 27th International Conference on Intelligent User Interfaces (IUI 2022)

Spreadsheet users regularly deal with uncertainty in their data, for example due to errors and estimates. While an insight into data uncertainty can help in making better informed decisions, prior research suggests that people often use informal heuristics to reason with probabilities, which leads to incorrect conclusions. Moreover, people often ignore or simplify uncertainty. To understand how people currently encounter and deal with uncertainty in spreadsheets, we conducted an interview study with 11 spreadsheet users from a range of domains. We found that how people deal with uncertainty is influenced by the role the spreadsheet plays in people's work and the user's aims. Spreadsheets are used as a database, template, calculation tool, notepad and exploration tool. In doing so, participants' aims were to compute and compare different scenarios, understand something about the nature of the uncertainty in their situation, and translate the complexity of data uncertainty into simplified presentations to other people, usually decision-makers. Spreadsheets currently provide limited tools to support these aims, and participants had various workarounds.