arXiv subjects

Hari Subramonyam

Publications and source records attributed to Hari Subramonyam.

16 recordsLinked to original sources

arXiv2026

ConvoLearn: A Learning Sciences Grounded Dataset for Fine-Tuning Dialogic AI Tutors

Despite their growing adoption in education, LLMs remain misaligned with the core principle of effective tutoring: the dialogic construction of knowledge. We introduce ConvoLearn, a dataset of 2,134 semi-synthetic tutor-student dialogues operationalizing six dimensions of dialogic tutoring grounded in knowledge-building theory, situated in a middle school Earth Science curriculum. We show that dimension-labeled dialogic training data captures meaningful pedagogical signal that generalizes beyond its semi-synthetic domain: scores from a classifier trained on ConvoLearn correlate significantly with expert-coded instructional quality in authentic classrooms across multiple subscales. As a proof of concept, we fine-tune Mistral-7B on ConvoLearn and show that dimension-level fine-tuning can steer a 7B open-weight model toward dialogic tutoring behavior that credentialed teachers rate as competitive with a strong proprietary baseline. With this work, we support the development of AI tutors capable of more dialogic interactions.

cs.AI↗

arXiv2026

Teaching Spell Checkers to Teach: Pedagogical Program Synthesis for Interactive Learning

Spelling taught through memorization often fails many learners, particularly children with language-based learning disorders who struggle with the phonological skills necessary to spell words accurately. Educators such as speech-language pathologists (SLPs) address this instructional gap by using an inquiry-based approach to teach spelling that targets the phonology, morphology, meaning, and etymology of words. Yet, these strategies rarely appear in everyday writing tools, which simply detect and autocorrect errors. We introduce SPIRE (Spelling Inquiry Engine), a spell check system that brings this inquiry-based pedagogy into the act of composition. SPIRE implements Pedagogical Program Synthesis, a novel approach for operationalizing the inherently dynamic pedagogy of spelling instruction. SPIRE represents SLP instructional moves in a domain-specific language, synthesizes tailored programs in real-time from learner errors, and renders them as interactive interfaces for inquiry-based interventions. With SPIRE, spelling errors become opportunities to explore word meanings, word structures, morphological families, word origins, and grapheme-phoneme correspondences, supporting metalinguistic reasoning alongside correction. Evaluation with SLPs and learners shows alignment with professional practice and potential for integration into writing workflows.

cs.HC↗

arXiv2025

DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces

As generative AI becomes part of everyday writing, questions of transparency and productive human effort are increasingly important. Educators, reviewers, and readers want to understand how AI shaped the process. Where was human effort focused? What role did AI play in the creation of the work? How did the interaction unfold? Existing approaches often reduce these dynamics to summary metrics or simplified provenance. We introduce DraftMarks, an augmented reading tool that surfaces the human-AI writing process through familiar physical metaphors. DraftMarks employs skeuomorphic encodings such as eraser crumbs to convey the intensity of revision, and masking tape or smudges to mark AI-generated content, simulating the process within the final written artifact. By using data from writer-AI interactions, DraftMarks' algorithm computes various collaboration metrics and writing traces. Through a formative study, we identified computational logic for different readership, and evaluated DraftMarks for its effectiveness in assessing AI co-authored writing.

cs.HC↗

arXiv2025

Understanding, Protecting, and Augmenting Human Cognition with Generative AI: A Synthesis of the CHI 2025 Tools for Thought Workshop

Generative AI (GenAI) radically expands the scope and capability of automation for work, education, and everyday tasks, a transformation posing both risks and opportunities for human cognition. How will human cognition change, and what opportunities are there for GenAI to augment it? Which theories, metrics, and other tools are needed to address these questions? The CHI 2025 workshop on Tools for Thought aimed to bridge an emerging science of how the use of GenAI affects human thought, from metacognition to critical thinking, memory, and creativity, with an emerging design practice for building GenAI tools that both protect and augment human thought. Fifty-six researchers, designers, and thinkers from across disciplines as well as industry and academia, along with 34 papers and portfolios, seeded a day of discussion, ideation, and community-building. We synthesize this material here to begin mapping the space of research and design opportunities and to catalyze a multidisciplinary community around this pressing area of research.

cs.HC↗

arXiv2025

SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations

Programming-by-prompting with generative AI offers a new paradigm for end-user programming, shifting the focus from syntactic fluency to semantic intent. This shift holds particular promise for non-programmers such as educators, who can describe instructional goals in natural language to generate interactive learning content. Yet in bypassing direct code authoring, many of programming's core affordances - such as traceability, stepwise refinement, and behavioral testing - are lost. We propose the Chain-of-Abstractions (CoA) framework as a way to recover these affordances while preserving the expressive flexibility of natural language. CoA decomposes the synthesis process into a sequence of cognitively meaningful, task-aligned representations that function as checkpoints for specification, inspection, and refinement. We instantiate this approach in SimStep, an authoring environment for teachers that scaffolds simulation creation through four intermediate abstractions: Concept Graph, Scenario Graph, Learning Goal Graph, and UI Interaction Graph. To address ambiguities and misalignments, SimStep includes an inverse correction process that surfaces in-filled model assumptions and enables targeted revision without requiring users to manipulate code. Evaluations with educators show that CoA enables greater authoring control and interpretability in programming-by-prompting workflows.

cs.HC↗

arXiv2025

AI in the Writing Process: How Purposeful AI Support Fosters Student Writing

The ubiquity of technologies like ChatGPT has raised concerns about their impact on student writing, particularly regarding reduced learner agency and superficial engagement with content. While standalone chat-based LLMs often produce suboptimal writing outcomes, evidence suggests that purposefully designed AI writing support tools can enhance the writing process. This paper investigates how different AI support approaches affect writers' sense of agency and depth of knowledge transformation. Through a randomized control trial with 90 undergraduate students, we compare three conditions: (1) a chat-based LLM writing assistant, (2) an integrated AI writing tool to support diverse subprocesses, and (3) a standard writing interface (control). Our findings demonstrate that, among AI-supported conditions, students using the integrated AI writing tool exhibited greater agency over their writing process and engaged in deeper knowledge transformation overall. These results suggest that thoughtfully designed AI writing support targeting specific aspects of the writing process can help students maintain ownership of their work while facilitating improved engagement with content.

cs.HC↗

arXiv2025

CogGen: A Learner-Centered Generative AI Architecture for Intelligent Tutoring with Programming Video

We introduce CogGen, a learner-centered AI architecture that transforms programming videos into interactive, adaptive learning experiences by integrating student modeling with generative AI tutoring based on the Cognitive Apprenticeship framework. The architecture consists of three components: (1) video segmentation by learning goals, (2) a conversational tutoring engine applying Cognitive Apprenticeship strategies, and (3) a student model using Bayesian Knowledge Tracing to adapt instruction. Our technical evaluation demonstrates effective video segmentation accuracy and strong pedagogical alignment across knowledge, method, action, and interaction layers. Ablation studies confirm the necessity of each component in generating effective guidance. This work advances AI-powered tutoring by bridging structured student modeling with interactive AI conversations, offering a scalable approach to enhancing video-based programming education.

cs.AI↗

arXiv2025

Thinking Like a Scientist: Can Interactive Simulations Foster Critical AI Literacy?

As AI systems shape individual and societal decisions, fostering critical AI literacy is essential. Traditional approaches, such as blog articles, static lessons, and social media discussions, often fail to support deep conceptual understanding and critical engagement. This study examines whether interactive simulations can help learners think like a scientist by engaging them in hypothesis testing, experimentation, and direct observation of AI behavior. In a controlled study with 605 participants, we assess how interactive AI tutorials impact learning of key concepts such as fairness, dataset representativeness, and bias in language models. Results show that interactive simulations effectively enhance AI literacy across topics, supporting greater knowledge transfer and self-reported confidence, though engagement alone does not predict learning. This work contributes to the growing field of AI literacy education, highlighting how interactive, inquiry-driven methodologies can better equip individuals to critically engage with AI in their daily lives.

cs.HC↗

arXiv2025

Prototyping with Prompts: Emerging Approaches and Challenges in Generative AI Design for Collaborative Software Teams

Generative AI models are increasingly being integrated into human task workflows, enabling the production of expressive content across a wide range of contexts. Unlike traditional human-AI design methods, the new approach to designing generative capabilities focuses heavily on prompt engineering strategies. This shift requires a deeper understanding of how collaborative software teams establish and apply design guidelines, iteratively prototype prompts, and evaluate them to achieve specific outcomes. To explore these dynamics, we conducted design studies with 39 industry professionals, including UX designers, AI engineers, and product managers. Our findings highlight emerging practices and role shifts in AI system prototyping among multistakeholder teams. We observe various prompting and prototyping strategies, highlighting the pivotal role of to-be-generated content characteristics in enabling rapid, iterative prototyping with generative AI. By identifying associated challenges, such as the limited model interpretability and overfitting the design to specific example content, we outline considerations for generative AI prototyping.

cs.HC↗

arXiv2025

Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems

Generative AI systems such as ChatGPT and Claude are built upon language models that are typically evaluated for accuracy on curated benchmark datasets. Such evaluation paradigms measure predictive and reasoning capabilities of language models but do not assess if they can provide information that is useful to people. In this paper, we take some initial steps in developing an evaluation paradigm that centers human understanding and decision-making. We study the utility of generative AI systems in supporting people in a concrete task - making sense of clinical reports and imagery in order to make a clinical decision. We conducted a formative need-finding study in which participants discussed chest computed tomography (CT) scans and associated radiology reports of a fictitious close relative with a cardiothoracic radiologist. Using thematic analysis of the conversation between participants and medical experts, we identified commonly occurring themes across interactions, including clarifying medical terminology, locating the problems mentioned in the report in the scanned image, understanding disease prognosis, discussing the next diagnostic steps, and comparing treatment options. Based on these themes, we evaluated two state-of-the-art generative AI systems against the radiologist's responses. Our results reveal variability in the quality of responses generated by the models across various themes. We highlight the importance of patient-facing generative AI systems to accommodate a diverse range of conversational themes, catering to the real-world informational needs of patients.

cs.HC↗

arXiv2025

Script&Shift: A Layered Interface Paradigm for Integrating Content Development and Rhetorical Strategy with LLM Writing Assistants

Good writing is a dynamic process of knowledge transformation, where writers refine and evolve ideas through planning, translating, and reviewing. Generative AI-powered writing tools can enhance this process but may also disrupt the natural flow of writing, such as when using LLMs for complex tasks like restructuring content across different sections or creating smooth transitions. We introduce Script&Shift, a layered interface paradigm designed to minimize these disruptions by aligning writing intents with LLM capabilities to support diverse content development and rhetorical strategies. By bridging envisioning, semantic, and articulatory distances, Script&Shift's interactions allow writers to leverage LLMs for various content development tasks (scripting) and experiment with diverse organization strategies while tailoring their writing for different audiences (shifting). This approach preserves creative control while encouraging divergent and iterative writing. Our evaluation shows that Script&Shift enables writers to creatively and efficiently incorporate LLMs while preserving a natural flow of composition.

cs.HC↗

arXiv2024

Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than Answering

Many AI systems focus solely on providing solutions or explaining outcomes. However, complex tasks like research and strategic thinking often benefit from a more comprehensive approach to augmenting the thinking process rather than passively getting information. We introduce the concept of "Thinking Assistant", a new genre of assistants that help users improve decision-making with a combination of asking reflection questions based on expert knowledge. Through our lab study (N=80), these Large Language Model (LLM) based Thinking Assistants were better able to guide users to make important decisions, compared with conversational agents that only asked questions, provided advice, or neither. Based on the results, we develop a Thinking Assistant in academic career development, determining research trajectory or developing one's unique research identity, which requires deliberation, reflection and experts' advice accordingly. In a longitudinal deployment with 223 conversations, participants responded positively to approximately 65% of the responses. Our work proposes directions for developing more effective LLM agents. Rather than adhering to the prevailing authoritative approach of generating definitive answers, LLM agents aimed at assisting with cognitive enhancement should prioritize fostering reflection. They should initially provide responses designed to prompt thoughtful consideration through inquiring, followed by offering advice only after gaining a deeper understanding of the user's context and needs.

cs.HC↗

arXiv2024

A Conceptual Framework for Ethical Evaluation of Machine Learning Systems

Research in Responsible AI has developed a range of principles and practices to ensure that machine learning systems are used in a manner that is ethical and aligned with human values. However, a critical yet often neglected aspect of ethical ML is the ethical implications that appear when designing evaluations of ML systems. For instance, teams may have to balance a trade-off between highly informative tests to ensure downstream product safety, with potential fairness harms inherent to the implemented testing procedures. We conceptualize ethics-related concerns in standard ML evaluation techniques. Specifically, we present a utility framework, characterizing the key trade-off in ethical evaluation as balancing information gain against potential ethical harms. The framework is then a tool for characterizing challenges teams face, and systematically disentangling competing considerations that teams seek to balance. Differentiating between different types of issues encountered in evaluation allows us to highlight best practices from analogous domains, such as clinical trials and automotive crash testing, which navigate these issues in ways that can offer inspiration to improve evaluation processes in ML. Our analysis underscores the critical need for development teams to deliberately assess and manage ethical complexities that arise during the evaluation of ML systems, and for the industry to move towards designing institutional policies to support ethical evaluations.

cs.CY↗

arXiv2024

AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired People

People with visual impairments often struggle to create content that relies heavily on visual elements, particularly when conveying spatial and structural information. Existing accessible drawing tools, which construct images line by line, are suitable for simple tasks like math but not for more expressive artwork. On the other hand, emerging generative AI-based text-to-image tools can produce expressive illustrations from descriptions in natural language, but they lack precise control over image composition and properties. To address this gap, our work integrates generative AI with a constructive approach that provides users with enhanced control and editing capabilities. Our system, AltCanvas, features a tile-based interface enabling users to construct visual scenes incrementally, with each tile representing an object within the scene. Users can add, edit, move, and arrange objects while receiving speech and audio feedback. Once completed, the scene can be rendered as a color illustration or as a vector for tactile graphic generation. Involving 14 blind or low-vision users in design and evaluation, we found that participants effectively used the AltCanvas workflow to create illustrations.

cs.HC↗

arXiv2024

Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs

Online programming videos, including tutorials and streamcasts, are widely popular and contain a wealth of expert knowledge. However, effectively utilizing these resources to achieve targeted learning goals can be challenging. Unlike direct tutoring, video content lacks tailored guidance based on individual learning paces, personalized feedback, and interactive engagement necessary for support and monitoring. Our work transforms programming videos into one-on-one tutoring experiences using the cognitive apprenticeship framework. Tutorly, developed as a JupyterLab Plugin, allows learners to (1) set personalized learning goals, (2) engage in learning-by-doing through a conversational LLM-based mentor agent, (3) receive guidance and feedback based on a student model that steers the mentor moves. In a within-subject study with 16 participants learning exploratory data analysis from a streamcast, Tutorly significantly improved their performance from 61.9% to 76.6% based on a post-test questionnaire. Tutorly demonstrates the potential for enhancing programming video learning experiences with LLM and learner modeling.

cs.HC↗

arXiv2024

Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants.

cs.HC↗