Search for: All records

This project examines the prospect of using AI-generated feedback as suggestions to expedite and enhance human instructors’ feedback provision. In particular, we focus on understanding the teaching assistants’ perspectives on the quality of AI-generated feedback and how they may or may not utilize AI feedback in their own workflows. We situate our work in a foundational college Economics class, which has frequent short essay assignments. We developed an LLM-powered feedback engine that generates feedback on students’ essays based on grading rubrics used by the teaching assistants (TAs). To ensure that TAs can meaningfully critique and engage with the AI feedback, we had them complete their regular grading jobs. For a randomly selected set of essays that they had graded, we used our feedback engine to generate feedback and displayed the feedback as in-text comments in a Word document. We then performed think-aloud studies with 5 TAs over 20 1-hour sessions to have them evaluate the AI feedback, contrast the AI feedback with their handwritten feedback, and share how they envision using the AI feedback if they were offered as suggestions. The study highlights the importance of providing detailed rubrics for AI to generate high-quality feedback for knowledge-intensive essays. TAs considered that using AI feedback as suggestions during their grading could expedite grading, enhance consistency, and improve overall feedback quality. We discuss the importance of decomposing the feedback generation task into steps and presenting intermediate results, in order for TAs to use the AI feedback. 

This project examines the prospect of using AI-generated feedback as suggestions to expedite and enhance human instructors’ feedback provision. In particular, we focus on understanding the teaching assistants’ perspectives on the quality of AI-generated feedback and how they may or may not utilize AI feedback in their own workflows. We situate our work in a foundational college Economics class, which has frequent short essay assignments. We developed an LLM-powered feedback engine that generates feedback on students’ essays based on grading rubrics used by the teaching assistants (TAs). To ensure that TAs can meaningfully critique and engage with the AI feedback, we had them complete their regular grading jobs. For a randomly selected set of essays that they had graded, we used our feedback engine to generate feedback and displayed the feedback as in-text comments in a Word document. We then performed think-aloud studies with 5 TAs over 20 1-hour sessions to have them evaluate the AI feedback, contrast the AI feedback with their handwritten feedback, and share how they envision using the AI feedback if they were offered as suggestions. The study highlights the importance of providing detailed rubrics for AI to generate high-quality feedback for knowledge-intensive essays. TAs considered that using AI feedback as suggestions during their grading could expedite grading, enhance consistency, and improve overall feedback quality. We discuss the importance of decomposing the feedback generation task into steps and presenting intermediate results, in order for TAs to use the AI feedback. 

Abstract We report a series of shape‐persistent molecular nanotubes with top rim connectivity traversing from an all‐meta‐ (m₄) to an all‐para‐phenylene (p₄) bridged species, including all possible members in between them. Single‐crystal X‐ray diffraction (SCXRD) and microcrystal electron diffraction (MicroED) data show a large torsional angle formeta‐phenylenes relative topara‐phenylene rings. Density functional theory (DFT) calculations reproduce the experimental torsional angles and also establish a correlation indicating a gradual increase in strain energy fromm₄(∼31 kcal mol⁻¹) top₄(∼90 kcal mol⁻¹). Structural transitions fromm₄top₄lead to additional correlations such as a shift in the lowest absorption wavelength from 330 to 394 nm, a sizeable red shift in the maximum emission wavelength from 444 to 546 nm, and a decrease in fluorescence quantum yield from 0.76 to 0.20, respectively. Time‐dependent (TD)‐DFT analysis of the relaxed excited state (S_1’) geometry shows a progression of exciton delocalization aspara‐phenylenes are introduced intom₄en route top₄, while the overall molecular size remains constant. This effect is directly related to increased π‐conjugation within the nanotube's top‐segment and demonstrates how exciton trapping can take place without changing the nanotube's physical size, e.g., diameter and length. 

Evaluating the quality of automatically generated question items has been a long standing challenge. In this paper, we leverage LLMs to simulate student profiles and generate responses to multiple-choice questions (MCQs). The generative students' responses to MCQs can further support question item evaluation. We propose Generative Students, a prompt architecture designed based on the KLI framework. A generative student profile is a function of the list of knowledge components the student has mastered, has confusion about or has no evidence of knowledge of. We instantiate the Generative Students concept on the subject domain of heuristic evaluation. We created 45 generative students using GPT-4 and had them respond to 20 MCQs. We found that the generative students produced logical and believable responses that were aligned with their profiles. We then compared the generative students' responses to real students' responses on the same set of MCQs and found a high correlation. Moreover, there was considerable overlap in the difficult questions identified by generative students and real students. A subsequent case study demonstrated that an instructor could improve question quality based on the signals provided by Generative Students. 

Abstract Herein, we report the synthesis of a new series of rigid, allmeta‐phenylene, conjugated deep‐cavity molecules, displaying high binding affinity towards buckyballs. A facile synthetic approach with an overall combined yield of approximately 53% in the last two steps has been developed using a templating strategy that combines the general structure of resorcin[4]arene and [12]cyclo‐meta‐phenylene. These two moieties are covalently linked via four acetal bonds, resulting in a glove‐like architecture.¹H NMR titration experiments reveal fullerene binding affinities (K_a) exceeding ≥10⁶ M⁻¹. The size complementarity between fullerenes and these scaffolds maximizes CH⋯π and π⋯π interactions, and their host:guest adduct resembles a ball in a glove, hence their name as nanogloves. Fullerene recognition is tested by suspending carbon soot in a solution of nanoglove in 1,1,2,2‐tetrachloroethane, where more than a dozen fullerenes are observed, ranging from C₆₀to C₉₆.