CoTAL: New Method Uses AI and Teacher Feedback to Improve Student Assessment Scoring Across Subjects
Researchers introduced CoTAL, a system combining large language models with human feedback to automatically score student work and provide explanations. The approach uses chain-of-thought prompting and iterative refinement guided by teachers and students to improve accuracy. The method showed significant performance gains and could help educators scale formative assessment across science, computing, and engineering domains.
A new study published on arXiv presents CoTAL (Chain-of-Thought Prompting + Active Learning), an LLM-based system designed to automate formative assessment scoring while maintaining alignment with curriculum goals. The approach combines three key elements: Evidence-Centered Design to connect assessments with learning objectives, human-in-the-loop prompt engineering where teachers and students iteratively refine the system, and chain-of-thought prompting to improve reasoning transparency. Testing with GPT-4 demonstrated performance improvements of up to 38.9% compared to baseline LLM scoring without these enhancements. Both teachers and students rated the system as effective for scoring responses and generating explanations. The research addresses a gap in understanding how prompt engineering techniques generalize across different educational domains.
Limitations & open questions
The study's own limitations and scope constraints are not detailed in the abstract provided. Specific information about sample size, number of domains tested, types of student responses evaluated, and any failure cases or domain-specific challenges would clarify the generalizability claims. The abstract does not specify which grade levels or student populations were involved in the evaluation.
What different sources said
- arXiv cs.CLCenter
CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback
Related
Study Identifies D-Retro-Inverso Peptides as Potential Treatments for Cardiac Amyloidosis
Researchers designed four peptide candidates using D-amino acids to inhibit Serum Amyloid A (SAA) fibril formation, which may contribute to complications following heart attacks. The study, conducted using molecular dynamics simulations in a mouse model, identified two peptides—DRI-R5S and DRI-H6A—as promising drug candidates. This work could lead to new therapeutic approaches for cardiac amyloidosis, a serious post-infarction complication.
Scientists Discover Previously Unknown Branch of Tryptophan Metabolism in Humans
Researchers identified a new enzymatic step in human tryptophan catabolism, showing that the protein ASPDH acts as a 2-aminomuconate reductase to produce a previously unknown amino acid. This discovery fills a gap in the kynurenine pathway, one of the body's major metabolic routes for processing the amino acid tryptophan. The finding expands understanding of human metabolism and may have implications for understanding NAD cofactor production and related metabolic diseases.
Japanese researchers find Adelie penguins use group behavior to locate new foraging grounds
A Japanese research team discovered that Adelie penguins in Antarctica follow colony members to find new feeding areas after unsuccessful foraging attempts. The study analyzed data from 116 penguins fitted with activity recorders in Lutzow-Holm Bay and was published in Proceedings of the Royal Society B. The findings demonstrate how group living provides foraging advantages and may help explain the evolution of social behavior in animals.