The study explores how undergraduate computing students in Saudi Arabia perceive AI‑generated writing feedback when they are explicitly told that ChatGPT, not a human instructor, produced the score and comments. Through qualitative reflections, four themes emerged: students found the feedback useful for surface‑level revisions, recognized AI’s contextual and pedagogical limits, trusted the feedback conditionally—separating its utility from its authority—and reaffirmed the human instructor’s role as the ultimate grading authority. The findings highlight a clear distinction students make between feedback usefulness and evaluative authority, treating them as separate judgments rather than opposing ends of a single approval scale.
By Rayed AlGhamdi
arXiv:2607. 01247v1 Announce Type: cross Abstract: Open-ended mathematics exams are valuable because they assess reasoning, proof construction, algorithmic thinking, and communication of intermediate steps.
By Aastha Sapkota, M. G. Sarwar Murshed
arXiv:2608.28626v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly used to generate peer reviews, prompting examination of their capacity for critical evaluation. This st...
By Emad Alharbi
arXiv:2603.17839v4 Announce Type: replace-cross
Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from...
By Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Veli\v{c}kovi\'c
The paper examines whether state‑of‑the‑art large language models (LLMs) produce feedback that aligns with expert teachers’ pedagogical practices, focusing on feedback type and adaptivity. Using a refined taxonomy of seven feedback focus types, the authors annotate and compare teacher and LLM‑generated feedback from three university writing courses, creating the FeedType benchmark. Their analysis shows that while most LLMs cover many feedback types, they do not match teachers’ distribution patterns or adaptive behavior across draft stages and student performance levels.
By Norah Almousa, Shayan Peyghambari Oskoui, Raquel Coelho, Gayle Rogers, Xiang Lorraine Li, Diane Litman
The paper reports a structured case study in which six frontier language models were asked to match handwritten exam answers to the ages of the writers. Three of the models performed at chance on the matching task while still reporting high confidence, and the youngest writer’s answer was misattributed to an adult in up to 90% of trials. Removing the multiple‑choice scaffold and changing institutional framing further degraded accuracy, while a single audience‑awareness instruction improved performance for one model but had no effect on the weakest models.
By Brianne Lee
arXiv:2608.29517v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used as essay graders in learning analytics, evaluated almost exclusively with agreement statistics. Educ...
By Veerendra Kumar Sunkavalli
This scoping review examines 421 studies (2015‑2026) on natural language processing applied to student evaluation of teaching comments. It maps the technical evolution from lexicons and classifiers to transformers and large language models, and evaluates four value dimensions. The review identifies a significant gap between actionable outputs (61.3%) and intended‑user evaluation (11.6%), highlighting limited progress in educational value and robustness.
By Jeff Eicher, Rafael da Silva
arXiv:2610.31679v1 Announce Type: new
Abstract: Large language models are increasingly used as math tutors, raising two questions: can a single LLM detect a student's error, diagnose the underlying m...
By Woojin Lee, Yoonkyu Woo, Jinah Kim, Hyeok-Min Gwon, Jin-Xia Huang
The study compares two ways of obtaining predictions from language models fine‑tuned on customer behavior: scoring answer tokens directly versus generating a written rationale and then scoring the resulting answer. Across 13 model‑domain cells covering four retail tasks, scored readouts consistently rank outcomes more accurately than generated readouts, with an AUC improvement ranging from 1.5 to 14.5 points. The authors also find that a third readout—eliciting a probability before any verdict—improves calibration but only when outcome rates are represented in training, and they recommend using generated rationales for interpretability while relying on scored heads for ranking.
By Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua
arXiv:2609.14284v1 Announce Type: new
Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Th...
By Md Khalid Syfullah, Asif Hasan Tonmoy, Saad Ahmed, S. M. Jahangir Alam
The report audits a long‑term‑memory retrieval chain on 500 LongMemEval‑S development questions, evaluating reader performance under an adapted GPT‑4o rubric. Scores vary widely across reader lanes (93–479), with the strongest lanes scoring 479 and 475, and re‑judging the same pass‑1 answers changes three labels, yielding 478. Fixed‑answer knowledge‑update re‑scoring achieves 70/72 or 69/72 depending on the template, and a different‑family reader scores 474, just 1.0 percentage point below the headline pass. The study also reports that live reader request bodies were not retained, that 18 of 23 gains occurred where baseline packets lacked evidence, and that a negative control rejects a verifier that repairs some wrong drafts but breaks many correct ones. Overall, the findings do not establish a new leaderboard leader or a transferable memory advantage, and the released artifacts support packet inspection and re‑scoring but do not reconstruct the method.
By Christopher J. Chanhnourack