CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring

• URL: http://arxiv.org/abs/2504.02323v3
• Date: Wed, 13 Aug 2025 23:53:03 GMT
• Title: CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring
• Authors: Clayton Cohn, Ashwin T S, Naveeduddin Mohammed, Gautam Biswas,
• Abstract summary: Chain-of-Thought Prompting + Active Learning (CoTAL) is an Evidence-Centered Design (ECD)-based approach to formative assessment scoring.<n>Our findings demonstrate that CoTAL improves GPT-4's scoring performance across domains.
• Score: 2.249916681499244
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various prompt engineering approaches in educational contexts, the degree to which these approaches generalize across domains--such as science, computing, and engineering--remains underexplored. In this paper, we introduce Chain-of-Thought Prompting + Active Learning (CoTAL), an LLM-based approach to formative assessment scoring that (1) leverages Evidence-Centered Design (ECD) to align assessments and rubrics with curriculum goals, (2) applies human-in-the-loop prompt engineering to automate response scoring, and (3) incorporates chain-of-thought (CoT) prompting and teacher and student feedback to iteratively refine questions, rubrics, and LLM prompts. Our findings demonstrate that CoTAL improves GPT-4's scoring performance across domains, achieving gains of up to 38.9% over a non-prompt-engineered baseline (i.e., without labeled examples, chain-of-thought prompting, or iterative refinement). Teachers and students judge CoTAL to be effective at scoring and explaining responses, and their feedback produces valuable insights that enhance grading accuracy and explanation quality.

Related papers

• LLM Prompt Evaluation for Educational Applications [2.1883807277376754]
  Large language models (LLMs) are increasingly common in educational applications.<n>There is a growing need for evidence-based methods to design and evaluate LLM prompts.<n>This study presents a generalizable, systematic approach for evaluating prompts.
  arXiv  Detail & Related papers  (2026-01-22T17:31:25Z)
• Exposía: Academic Writing Assessment of Exposés and Peer Feedback [56.428320613219306]
  We present Exposa, the first public dataset that connects writing and feedback assessment in higher education.<n>We use Exposa to benchmark state-of-the-art open-source large language models (LLMs) for two tasks: automated scoring of (1) the proposals and (2) the student reviews.
  arXiv  Detail & Related papers  (2026-01-10T11:33:26Z)
• Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology [0.0]
  We present an empirical framework for optimizing prompt performance for identifying constructs in texts via prompt engineering.<n>We experimentally evaluate five prompting strategies -codebook-guided empirical prompt selection, automatic prompt engineering, persona prompting, chain-of-thought reasoning, and explanatory prompting.<n>Across three constructs and two models, the classifications most aligned with expert judgments resulted from a few-shot prompt combining codebook-guided empirical prompt selection with automatic prompt engineering.
  arXiv  Detail & Related papers  (2025-12-03T14:07:42Z)
• Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper [64.50822834679101]
  SciIG is a task that evaluates LLMs' ability to produce coherent introductions from titles, abstracts, and related works.<n>We assess five state-of-the-art models, including open-source (DeepSeek-v3, Gemma-3-12B, LLaMA 4-Maverick, MistralAI Small 3.1) and closed-source GPT-4o systems.<n>Results demonstrate LLaMA-4 Maverick's superior performance on most metrics, particularly in semantic similarity and faithfulness.
  arXiv  Detail & Related papers  (2025-08-19T21:11:11Z)
• Teaching Language Models To Gather Information Proactively [53.85419549904644]
  Large language models (LLMs) are increasingly expected to function as collaborative partners.<n>In this work, we introduce a new task paradigm: proactive information gathering.<n>We design a scalable framework that generates partially specified, real-world tasks, masking key information.<n>Within this setup, our core innovation is a reinforcement finetuning strategy that rewards questions that elicit genuinely new, implicit user information.
  arXiv  Detail & Related papers  (2025-07-28T23:50:09Z)
• Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development [5.559706293891474]
  Large language model (LLM)-powered chatbots have become popular across various domains, supporting a range of tasks and processes.<n>Yet, prompting is highly task- and domain-dependent, limiting the effectiveness of generic approaches.<n>In this study, we explore whether LLM-based methods can facilitate learning assessments by using ad-hoc guidelines and a minimal number of annotated prompt samples.
  arXiv  Detail & Related papers  (2025-03-04T11:56:33Z)
• PanguIR Technical Report for NTCIR-18 AEOLLM Task [12.061652026366591]
  Large language models (LLMs) are increasingly critical and challenging to evaluate.<n>Manual evaluation, while comprehensive, is often costly and resource-intensive.<n>automatic evaluation offers greater scalability but is constrained by the limitations of its evaluation criteria.
  arXiv  Detail & Related papers  (2025-03-04T07:40:02Z)
• Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course [0.0]
  Natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback.<n>Recent advances in natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback.<n>Our results show that with well-designed prompts, LLMs can achieve grading accuracy and feedback quality comparable to human graders.
  arXiv  Detail & Related papers  (2025-01-24T13:59:14Z)
• A Zero-Shot LLM Framework for Automatic Assignment Grading in Higher Education [0.6141800972050401]
  We propose a Zero-Shot Large Language Model (LLM)-Based Automated Assignment Grading (AAG) system. This framework leverages prompt engineering to evaluate both computational and explanatory student responses without requiring additional training or fine-tuning. The AAG system delivers tailored feedback that highlights individual strengths and areas for improvement, thereby enhancing student learning outcomes.
  arXiv  Detail & Related papers  (2025-01-24T08:01:41Z)
• CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback [0.0]
  This study presents an automated grading framework, CodEv, which leverages Large Language Models (LLMs) to provide consistent and constructive feedback.<n>Our framework also integrates LLM ensembles to improve the accuracy and consistency of scores, along with agreement tests to deliver reliable feedback and code review comments.
  arXiv  Detail & Related papers  (2025-01-10T03:09:46Z)
• MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs [97.94579295913606]
  Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia.<n>In the development process, evaluation is critical since it provides intuitive feedback and guidance on improving models.<n>This work aims to offer researchers an easy grasp of how to effectively evaluate MLLMs according to different needs and to inspire better evaluation methods.
  arXiv  Detail & Related papers  (2024-11-22T18:59:54Z)
• Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course [49.296957552006226]
  Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. This report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students.
  arXiv  Detail & Related papers  (2024-07-07T00:17:24Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science [3.124884279860061]
  Our study focuses on employing GPT-4 for automated assessment in middle school Earth Science. A systematic analysis of our method's pros and cons sheds light on the potential for human-in-the-loop techniques to enhance automated grading.
  arXiv  Detail & Related papers  (2024-03-21T17:09:08Z)
• KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions [63.307317584926146]
  Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly common instruction-following task: providing writing assistance to compose a long-form answer. We construct KIWI, a dataset of knowledge-intensive writing instructions in the scientific domain.
  arXiv  Detail & Related papers  (2024-03-06T17:16:44Z)
• Evaluating and Optimizing Educational Content with Large Language Model Judgments [52.33701672559594]
  We use Language Models (LMs) as educational experts to assess the impact of various instructions on learning outcomes. We introduce an instruction optimization approach in which one LM generates instructional materials using the judgments of another LM as a reward function. Human teachers' evaluations of these LM-generated worksheets show a significant alignment between the LM judgments and human teacher preferences.
  arXiv  Detail & Related papers  (2024-03-05T09:09:15Z)
• Improving the Validity of Automatically Generated Feedback via Reinforcement Learning [46.667783153759636]
  We propose a framework for feedback generation that optimize both correctness and alignment using reinforcement learning (RL)<n>Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO)
  arXiv  Detail & Related papers  (2024-03-02T20:25:50Z)
• Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection [13.608076739368949]
  We introduce a novel framework that harnesses the potential of large-scale pre-trained language models. Our framework processes the output of a typical few-shot chain-of-thought prompt, assesses the correctness of the response, scrutinizes the answer, and ultimately produces a new solution.
  arXiv  Detail & Related papers  (2023-10-08T06:36:26Z)
• TEMPERA: Test-Time Prompting via Reinforcement Learning [57.48657629588436]
  We propose Test-time Prompt Editing using Reinforcement learning (TEMPERA) In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge. Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods.
  arXiv  Detail & Related papers  (2022-11-21T22:38:20Z)
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback [54.142719510638614]
  In this paper, we frame the problem of providing feedback as few-shot classification. A meta-learner adapts to give feedback to student code on a new programming question from just a few examples by instructors. Our approach was successfully deployed to deliver feedback to 16,000 student exam-solutions in a programming course offered by a tier 1 university.
  arXiv  Detail & Related papers  (2021-07-23T22:41:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.