Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses

• URL: http://arxiv.org/abs/2603.04820v1
• Date: Thu, 05 Mar 2026 05:11:08 GMT
• Title: Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses
• Authors: Michael Hardy,
• Abstract summary: We show that the level of difficulty for human experts to perform the task of scoring written work of children has no observed statistical effect on LLM performance.<n>Specifically, we show that some scoring tasks measured as the easiest by human scorers were the hardest for LLMs.<n>Findings argue for systems design which better anticipates known statistical shortcomings of autoregressive models.
• Score: 4.061135251278187
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Automated short-answer scoring lags other LLM applications. We meta-analyze 890 culminating results across a systematic review of LLM short-answer scoring studies, modeling the traditional effect size of Quadratic Weighted Kappa (QWK) with mixed effects metaregression. We quantitatively illustrate that that the level of difficulty for human experts to perform the task of scoring written work of children has no observed statistical effect on LLM performance. Particularly, we show that some scoring tasks measured as the easiest by human scorers were the hardest for LLMs. Whether by poor implementation by thoughtful researchers or patterns traceable to autoregressive training, on average decoder-only architectures underperform encoders by 0.37--a substantial difference in agreement with humans. Additionally, we measure the contributions of various aspects of LLM technology on successful scoring such as tokenizer vocabulary size, which exhibits diminishing returns--potentially due to undertrained tokens. Findings argue for systems design which better anticipates known statistical shortcomings of autoregressive models. Finally, we provide additional experiments to illustrate wording and tokenization sensitivity and bias elicitation in high-stakes education contexts, where LLMs demonstrate racial discrimination. Code and data for this study are available.

Related papers

• The Erosion of LLM Signatures: Can We Still Distinguish Human and LLM-Generated Scientific Ideas After Iterative Paraphrasing? [0.7162422068114824]
  We evaluate the ability of state-of-the-art (SOTA) machine learning models to differentiate between human and LLM-generated ideas.<n>Our findings highlight the challenges SOTA models face in source attribution.
  arXiv  Detail & Related papers  (2025-12-04T23:22:21Z)
• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation [66.84286617519258]
  Large language models are transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis.<n>Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors.<n>We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant.
  arXiv  Detail & Related papers  (2025-09-10T17:58:53Z)
• What You See Is Not Always What You Get: An Empirical Study of Code Comprehension by Large Language Models [0.5735035463793009]
  We investigate the vulnerability of large language models (LLMs) to imperceptible attacks, where hidden character manipulation in source code misleads LLMs' behaviour while remaining undetectable to human reviewers.<n>These attacks include coding reordering, invisible coding characters, code deletions, and code homoglyphs.<n>Our findings confirm the susceptibility of LLMs to imperceptible coding character attacks, while different LLMs present different negative correlations between perturbation magnitude and performance.
  arXiv  Detail & Related papers  (2024-12-11T04:52:41Z)
• The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead? [60.01746782465275]
  Large Language Models (LLMs) have shown capabilities close to human performance in various analytical tasks. This paper investigates the efficiency and accuracy of LLMs in specialized tasks through a structured user study focusing on Human-LLM partnership.
  arXiv  Detail & Related papers  (2024-10-07T02:30:18Z)
• CoMMIT: Coordinated Multimodal Instruction Tuning [90.1532838391285]
  Multimodal large language models (MLLMs) generally involve cooperative learning between a backbone LLM and a feature encoder of non-text input modalities.<n>In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.<n>We propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness [39.57155321515097]
  Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. It remains unclear whether LLMs exhibit robustness in learning on graphs.
  arXiv  Detail & Related papers  (2024-07-16T09:05:31Z)
• Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring [21.7782670140939]
  Large language models (LLMs) have demonstrated strong potential in performing automatic scoring for constructed response assessments.<n>While constructed responses graded by humans are usually based on given grading rubrics, the methods by which LLMs assign scores remain largely unclear.<n>This paper uncovers the grading rubrics that LLMs used to score students' written responses to science tasks and their alignment with human scores.
  arXiv  Detail & Related papers  (2024-07-04T22:26:20Z)
• 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)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Are Large Language Models Good Statisticians? [10.42853117200315]
  StatQA is a new benchmark designed for statistical analysis tasks. We show that even state-of-the-art models such as GPT-4o achieve a best performance of only 64.83%. While open-source LLMs show limited capability, those fine-tuned ones exhibit marked improvements.
  arXiv  Detail & Related papers  (2024-06-12T02:23:51Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.