Sadhana Puntambekar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sadhana Puntambekar has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Dana Gnesdilow
University of Wisconsin-Madison, Madison, USA
10 shared publications - Indrani Dey
University of Wisconsin-Madison
5 shared publications - Rebecca Jane Passonneau
Pennsylvania State University
4 shared publications - Indrani Dey
University of Wisconsin-Madison, Madison, Wisconsin, USA
3 shared publications - Leanne Hirshfield
Institute of Cognitive Science, University of Colorado
3 shared publications - Mike Tissenbaum
University of Illinois Urbana-Champaign, Champaign, IL, USA
3 shared publications
Latest Publications
- 24 September 2026
- Published by Springer Nature in Educational Technology Research and Development
- p. 1-21
Unveiling the epistemic features and roles of digital tools through epistemic scaffolding
- 24 September 2026
- Published by Springer Nature in Educational Technology Research and Development
- p. 1-21
Unveiling the epistemic features and roles of digital tools through epistemic scaffolding
- Open Access
Instructional Goal-Aligned Question Generation for Student Evaluation in Virtual Lab Settings: How Closely Do LLMs Actually Align?
Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.
Open AccessInstructional Goal-Aligned Question Generation for Student Evaluation in Virtual Lab Settings: How Closely Do LLMs Actually Align?
Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.
- 20 July 2025
- Published by Springer Nature
- p. 76-82
A Comparative Analysis of LLM and Specialized NLP System for Automated Assessment of Science Content
- 20 July 2025
- Published by Springer Nature
- p. 76-82
A Comparative Analysis of LLM and Specialized NLP System for Automated Assessment of Science Content
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Piecing Together Teamwork: A Responsible Approach to an LLM-based Educational Jigsaw Agent
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessPiecing Together Teamwork: A Responsible Approach to an LLM-based Educational Jigsaw Agent
- Open Access
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 461-465
SimPal: Towards a Meta-Conversational Framework to Understand Teacher's Instructional Goals for K-12 Physics
Simulations are widely used to teach science in grade schools. These simulations are often augmented with a conversational artificial intelligence (AI) agent to provide real-time scaffolding support for students conducting experiments using the simulations. AI agents are highly tailored for each simulation, with a predesigned set of Instructional Goals (IGs), making it difficult for teachers to adjust IGs as the agent may no longer align with the revised IGs. Additionally, teachers are hesitant to adopt new third-party simulations for the same reasons. In this research, we introduce SimPal, a Large Language Model (LLM) based meta-conversational agent, to solve this misalignment issue between a pre-trained conversational AI agent and the constantly evolving pedagogy of instructors. Through natural conversation with SimPal, teachers first explain their desired IGs, based on which SimPal identifies a set of relevant physical variables and their relationships to create symbolic representations of the desired IGs. The symbolic representations can then be leveraged to design prompts for the original AI agent to yield better alignment with the desired IGs. We empirically evaluated SimPal using two LLMs: ChatGPT-3.5 and PaLM 2 on 63 Physics simulations from PhET and Golabz. Additionally, we examined the impact of different prompting techniques on LLM's performance by utilizing the TELeR taxonomy in identifying relevant physical variables for the IGs. Our findings showed that SimPal can do this task with a high degree of accuracy when provided with a well-defined prompt.
- 9 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 461-465
Open AccessSimPal: Towards a Meta-Conversational Framework to Understand Teacher's Instructional Goals for K-12 Physics
Simulations are widely used to teach science in grade schools. These simulations are often augmented with a conversational artificial intelligence (AI) agent to provide real-time scaffolding support for students conducting experiments using the simulations. AI agents are highly tailored for each simulation, with a predesigned set of Instructional Goals (IGs), making it difficult for teachers to adjust IGs as the agent may no longer align with the revised IGs. Additionally, teachers are hesitant to adopt new third-party simulations for the same reasons. In this research, we introduce SimPal, a Large Language Model (LLM) based meta-conversational agent, to solve this misalignment issue between a pre-trained conversational AI agent and the constantly evolving pedagogy of instructors. Through natural conversation with SimPal, teachers first explain their desired IGs, based on which SimPal identifies a set of relevant physical variables and their relationships to create symbolic representations of the desired IGs. The symbolic representations can then be leveraged to design prompts for the original AI agent to yield better alignment with the desired IGs. We empirically evaluated SimPal using two LLMs: ChatGPT-3.5 and PaLM 2 on 63 Physics simulations from PhET and Golabz. Additionally, we examined the impact of different prompting techniques on LLM's performance by utilizing the TELeR taxonomy in identifying relevant physical variables for the IGs. Our findings showed that SimPal can do this task with a high degree of accuracy when provided with a well-defined prompt.
- 2 July 2024
- Published by Springer Nature
- p. 225-233
How Well Can You Articulate that Idea? Insights from Automated Formative Assessment
- 2 July 2024
- Published by Springer Nature
- p. 225-233
How Well Can You Articulate that Idea? Insights from Automated Formative Assessment
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
A Plant Simulation Tool for Collaborative Biology Experiments in Middle-school Classrooms: An In-the-wild Study
Computer-aided simulation-based platforms have been shown to be effective tools for teaching STEM concepts. At the same time, Computer Supported Collaborative Learning (CSCL) platforms encourage different viewpoints and approaches from the learners which can enrich the learning experience in STEM classrooms. The deployment in recent years of networked personal devices such as Chromebooks in classrooms has motivated educators to design collaborative learning tools for these devices. However, prior work has shown that using one-on-one devices may discourage students from talking among each other, which hinders collaboration. To understand the affordances of personal devices for CSCL tools within Biology curricula, we designed a collaborative plant growth simulation application that provides mirrored plant growth simulation views for every group member to facilitate a common visualization. In this paper, we present our findings from an in-the-wild study that evaluated the affordance and usability of the plant growth simulation application and investigated the nature of collaboration and engagement aided through the simulation mirroring feature. Our study results showed that the plant simulation application had high usability and acceptance. Moreover, mirroring the plant growth simulation improved collaboration, generated excitement, and stimulated conversation. We also identified episodes where collaboration was hindered due to off-task activities, troubleshooting, group dynamics, and lack of understanding that led us to outline some potential guidelines to improve the collaborative learning experience for the students in Biology classroom.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessA Plant Simulation Tool for Collaborative Biology Experiments in Middle-school Classrooms: An In-the-wild Study
Computer-aided simulation-based platforms have been shown to be effective tools for teaching STEM concepts. At the same time, Computer Supported Collaborative Learning (CSCL) platforms encourage different viewpoints and approaches from the learners which can enrich the learning experience in STEM classrooms. The deployment in recent years of networked personal devices such as Chromebooks in classrooms has motivated educators to design collaborative learning tools for these devices. However, prior work has shown that using one-on-one devices may discourage students from talking among each other, which hinders collaboration. To understand the affordances of personal devices for CSCL tools within Biology curricula, we designed a collaborative plant growth simulation application that provides mirrored plant growth simulation views for every group member to facilitate a common visualization. In this paper, we present our findings from an in-the-wild study that evaluated the affordance and usability of the plant growth simulation application and investigated the nature of collaboration and engagement aided through the simulation mirroring feature. Our study results showed that the plant simulation application had high usability and acceptance. Moreover, mirroring the plant growth simulation improved collaboration, generated excitement, and stimulated conversation. We also identified episodes where collaboration was hindered due to off-task activities, troubleshooting, group dynamics, and lack of understanding that led us to outline some potential guidelines to improve the collaborative learning experience for the students in Biology classroom.
- Open Access
How Well Can You Articulate that Idea? Insights from Automated Formative Assessment
Automated methods are becoming increasingly integrated into studies of formative feedback on students' science explanation writing. Most of this work, however, addresses students' responses to short answer questions. We investigate automated feedback on students' science explanation essays, where students must articulate multiple ideas. Feedback is based on a rubric that identifies the main ideas students are prompted to include in explanatory essays about the physics of energy and mass, given their experiments with a simulated roller coaster. We have found that students generally improve on revised versions of their essays. Here, however, we focus on two factors that affect the accuracy of the automated feedback. First, we find that the main ideas in the rubric differ with respect to how much freedom they afford in explanations of the idea, thus explanation of a natural law is relatively constrained. Students have more freedom in how they explain complex relations they observe in their roller coasters, such as transfer of different forms of energy. Second, by tracing the automated decision process, we can diagnose when a student's statement lacks sufficient clarity for the automated tool to associate it more strongly with one of the main ideas above all others. This in turn provides an opportunity for teachers and peers to help students reflect on how to state their ideas more clearly.
Open AccessHow Well Can You Articulate that Idea? Insights from Automated Formative Assessment
Automated methods are becoming increasingly integrated into studies of formative feedback on students' science explanation writing. Most of this work, however, addresses students' responses to short answer questions. We investigate automated feedback on students' science explanation essays, where students must articulate multiple ideas. Feedback is based on a rubric that identifies the main ideas students are prompted to include in explanatory essays about the physics of energy and mass, given their experiments with a simulated roller coaster. We have found that students generally improve on revised versions of their essays. Here, however, we focus on two factors that affect the accuracy of the automated feedback. First, we find that the main ideas in the rubric differ with respect to how much freedom they afford in explanations of the idea, thus explanation of a natural law is relatively constrained. Students have more freedom in how they explain complex relations they observe in their roller coasters, such as transfer of different forms of energy. Second, by tracing the automated decision process, we can diagnose when a student's statement lacks sufficient clarity for the automated tool to associate it more strongly with one of the main ideas above all others. This in turn provides an opportunity for teachers and peers to help students reflect on how to state their ideas more clearly.
- 17 January 2024
- Published by Ubiquity Press, Ltd. in Journal of Open Humanities Data
- Vol. 10
When Text and Speech are Not Enough: A Multimodal Dataset of Collaboration in a Situated Task
- 17 January 2024
- Published by Ubiquity Press, Ltd. in Journal of Open Humanities Data
- Vol. 10
When Text and Speech are Not Enough: A Multimodal Dataset of Collaboration in a Situated Task