An official website of the United States government
This research investigates students’ argumentation quality in engineering design thinking. We implemented Learning by Evaluating (LbE) using Adaptive Comparative Judgment (ACJ), where students assess pairs of items to determine the superior one. In ACJ, students provided rationales for their critiques, explaining their selections. Fifteen students participated in an LbE exercise before starting their backpack design projects, critically evaluating multiple backpack designs and producing 145 comments. Writing comments required students to discern and justify the superior design, fostering informed judgment and articulation of their reasoning. The study used the Claim, Evidence, and Reasoning (CER) framework, adapted for engineering design thinking, to analyse these critiques. The framework emphasized three aspects: Empathy (understanding user needs), Ideation (deriving design inspiration), and Insight (gaining valuable understanding from evaluated designs). We employed both deductive and inductive content analysis to evaluate the argumentation quality in students’ critiques. High-quality argumentation was identified based on six codes: user-focused empathy, design inspirations, logical rationalizations, multi-criteria evaluations, aesthetic considerations, and cultural awareness. Poor-quality argumentation lacked these elements and was characterized by vagueness, uncertainty, brevity, inappropriateness, irrelevance, gender bias, and cultural stereotyping. By identifying critical elements of effective argumentation and common challenges students may face, this study aims to enhance argumentation skills in engineering design thinking at the secondary education level. These insights are intended to help educators prepare students for insightful and successful argumentation in engineering design projects.
more »
« less
This content will become publicly available on August 1, 2026
LLMs can Perform Multi-Dimensional Analytic Writing Assessments
The paper explores the performance of LLMs in the context of multi-dimensional analytic writing assessments, i.e. their ability to provide both scores and comments based on multiple assessment criteria. Using a corpus of literature reviews written by L2 graduate students and assessed by human experts against 9 analytic criteria, we prompt several popular LLMs to perform the same task under various conditions. To evaluate the quality of feedback comments, we apply a novel feedback comment quality evaluation framework. This framework is interpretable, cost-efficient, scalable, and reproducible, compared to existing methods that rely on manual judgments. We find that LLMs can generate reasonably good and generally reliable multi-dimensional analytic assessments. We release our corpus and code\footnote{\url{https://github.com/jaaack-wang/multi-dimensional-analytic-writing-assessments}.} for reproducibility.
more »
« less
- Award ID(s):
- 2125295
- PAR ID:
- 10615151
- Publisher / Repository:
- ACM
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large Language Models (LLMs) have demonstrated unprecedented capability in code generation. However, LLM-generated code is still plagued with a wide range of functional errors, especially for complex programming tasks that LLMs have not seen before. Recent studies have shown that developers often struggle with inspecting and fixing incorrect code generated by LLMs, diminishing their productivity and trust in LLM-based code generation. Inspired by the mutual grounding theory in communication, we propose an interactive approach that leverages code comments as a medium for developers and LLMs to establish a shared understanding. Our approach facilitates iterative grounding by interleaving code generation, inline comment generation, and contextualized user feedback through editable comments to align generated code with developer intent. We evaluated our approach on two popular benchmarks and demonstrated that our approach significantly improved multiple state-of-the-art LLMs, e.g., 17.1% pass@1 improvement for code-davinci-002 on HumanEval. Furthermore, we conducted a user study with 12 participants in comparison to two baselines: (1) interacting with GitHub Copilot, and (2) interacting with a multi-step code generation paradigm called Multi-Turn Program Synthesis. Participants completed the given programming tasks 16.7% faster and with 10.5% improvement in task success rate when using our approach. Both results show that interactively refining code comments enables the collaborative establishment of mutual grounding, leading to more accurate code generation and higher developer confidence.more » « less
-
Medical systematic reviews play a vital role in healthcare decision making and policy. However, their production is time-consuming, limiting the availability of high-quality and up-to-date evidence summaries. Recent advancements in LLMs offer the potential to automatically generate literature reviews on demand, addressing this issue. However, LLMs sometimes generate inaccurate (and potentially misleading) texts by hallucination or omission. In healthcare, this can make LLMs unusable at best and dangerous at worst. We conducted 16 interviews with international systematic review experts to characterize the perceived utility and risks of LLMs in the specific context of medical evidence reviews. Experts indicated that LLMs can assist in the writing process by drafting summaries, generating templates, distilling information, and crosschecking information. They also raised concerns regarding confidently composed but inaccurate LLM outputs and other potential downstream harms, including decreased accountability and proliferation of low-quality reviews. Informed by this qualitative analysis, we identify criteria for rigorous evaluation of biomedical LLMs aligned with domain expert views.more » « less
-
Exposing students to low-quality assessments such as multiple-choice questions (MCQs) and short answer questions (SAQs) is detrimental to their learning, making it essential to accurately evaluate these assessments. Existing evaluation methods are often challenging to scale and fail to consider their pedagogical value within course materials. Online crowds offer a scalable and cost-effective source of intelligence, but often lack necessary domain expertise. Advancements in Large Language Models (LLMs) offer automation and scalability, but may also lack precise domain knowledge. To explore these trade-offs, we compare the effectiveness and reliability of crowdsourced and LLM-based methods for assessing the quality of 30 MCQs and SAQs across six educational domains using two standardized evaluation rubrics. We analyzed the performance of 84 crowdworkers from Amazon's Mechanical Turk and Prolific, comparing their quality evaluations to those made by the three LLMs: GPT-4, Gemini 1.5 Pro, and Claude 3 Opus. We found that crowdworkers on Prolific consistently delivered the highest-quality assessments, and GPT-4 emerged as the most effective LLM for this task. Our study reveals that while traditional crowdsourced methods often yield more accurate assessments, LLMs can match this accuracy in specific evaluative criteria. These results provide evidence for a hybrid approach to educational content evaluation, integrating the scalability of AI with the nuanced judgment of humans. We offer feasibility considerations in using AI to supplement human judgment in educational assessment.more » « less
-
Feedback is a critical aspect of improvement. Unfortunately, when there is a lot of feedback from multiple sources, it can be difficult to distill the information into actionable insights. Consider student evaluations of teaching (SETs), which are important sources of feedback for educators. These evaluations can provide instructors with insights into what worked and did not during a semester. A collection of SETs can also be useful to administrators as signals for courses or entire programs. However, on a large scale as in high-enrollment courses or administrative records over several years, the number of SETs can render them difficult to analyze. In this paper, we discuss a novel method for analyzing SETs using natural language processing (NLP) and large language models (LLMs). We demonstrate the method by applying it to a corpus of 5000 SETs from a large public university. We show that the method can extract, embed, cluster, and summarize the SETs to identify the themes they contain. More generally, this work illustrates how to use NLP techniques and LLMs to generate a codebook for SETs. We conclude by discussing the implications of this method for analyzing SETs and other types of student writing in teaching and research settings.more » « less
