Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation

• URL: http://arxiv.org/abs/2605.07647v1
• Date: Fri, 08 May 2026 12:12:01 GMT
• Title: Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
• Abstract summary: Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings.<n>We investigate the relationship between the degree of task-specific adaptation of different models and quality-conditioned scoring agreement.
• Score: 0.3078691410268859
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. This paradigm leverages LLMs broad world knowledge and ease of deployment, but limited task-specific data may reduce alignment on complex scoring tasks. In particular, its impact on scoring partially correct responses that require nuanced interpretation remains underexplored. We investigate the relationship between the degree of task-specific adaptation of different models and quality-conditioned scoring agreement. We compare three LLMs (GPT-5.2, GPT-4o, Claude Opus 4.5) in few-shot mode, a fine-tuned BERT-based encoder, and a human expert on two open-ended biology items, using several hundred student responses and ground truth scores provided by a biology education expert. The results show that human-human agreement is highest and stable across the full quality spectrum. All AI models perform well on fully correct and fully incorrect responses, but exhibit substantial degradation on mid-range responses. This mid-range degradation is conditioned on task-specific adaptation: It is most severe in few-shot LLMs with few examples and decreases as task-specific data increases, with fine-tuned encoder models performing best. This mid-range degradation may lead to inequitable evaluation of responses produced by students with developing understanding. Our findings highlight the importance of quality-conditioned fairness, with particular attention to mid-range responses.

Related papers

• Estimating LLM Grading Ability and Response Difficulty in Automatic Short Answer Grading via Item Response Theory [0.0]
  We introduce an evaluation framework for LLM-based ASAG based on item response theory (IRT)<n>IRT models grading correctness as a function of latent grader ability and response grading difficulty.<n>Results show that even models with similar overall performance differ substantially in how sharply their grading accuracy declines as response difficulty increases.
  arXiv  Detail & Related papers  (2026-04-30T21:16:59Z)
• Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, LLaMA [0.6263481844384227]
  This work proposes a systematic evaluation framework to examine how interaction tone affects model accuracy.<n>We apply this framework to three recently released and widely available large language models: GPT-4o mini (OpenAI), Gemini 2.0 Flash (Google DeepMind), and Llama 4 Scout (Meta)<n>Our results show that tone sensitivity is both model-dependent and domain-specific. Neutral or Very Friendly prompts generally yield higher accuracy than Very Rude prompts, but statistically significant effects appear only in a subset of Humanities tasks.
  arXiv  Detail & Related papers  (2025-12-14T19:25:20Z)
• CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs [81.79228604962687]
  This work investigates whether small-scale LMs can benefit from instruction tuning.<n>We compare conversational and question-answering instruction tuning datasets, applied either in a merged or sequential curriculum.<n>Results show that instruction tuning yields small but consistent gains in fine-tuning scenarios, with sequential curricula outperforming merged data.<n>However, improvements do not consistently transfer to zero-shot tasks, suggesting a trade-off between interaction-focused adaptation and broad linguistic generalization.
  arXiv  Detail & Related papers  (2025-10-29T10:36:39Z)
• Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam [41.99844472131922]
  In a large first-year exam, students' handwritten work was graded by GPT-5 against the same rubric used by teaching assistants (TAs)<n>We calibrated a human-in-the-loop filter that combines a partial-credit threshold with an Item Response Theory (2PL) risk measure based on the deviation between the AI score and the model-expected score for each student-item.<n>Unfiltered AI-TA agreement was moderate, adequate for low-stakes feedback but not for high-stakes use.
  arXiv  Detail & Related papers  (2025-10-04T15:07:06Z)
• AutoEvoEval: An Automated Framework for Evolving Close-Ended LLM Evaluation Data [0.6278186810520364]
  Large language models (LLMs) have shown remarkable performance on various tasks.<n>Existing evaluation benchmarks are often static and insufficient to fully assess their robustness and generalization.<n>We propose AutoEvoEval, an evolution-based evaluation framework for close-ended tasks such as question answering.
  arXiv  Detail & Related papers  (2025-06-30T11:18:56Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Language Models are Few-Shot Graders [0.12289361708127876]
  We present an ASAG pipeline leveraging state-of-the-art LLMs.<n>We compare the grading performance of three OpenAI models: GPT-4, GPT-4o, and o1-preview.<n>Our findings indicate that providing graded examples enhances grading accuracy, with RAG-based selection outperforming random selection.
  arXiv  Detail & Related papers  (2025-02-18T23:38:21Z)
• MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains [54.117238759317004]
  Massive Multitask Agent Understanding (MMAU) benchmark features comprehensive offline tasks that eliminate the need for complex environment setups. It evaluates models across five domains, including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics. With a total of 20 meticulously designed tasks encompassing over 3K distinct prompts, MMAU provides a comprehensive framework for evaluating the strengths and limitations of LLM agents.
  arXiv  Detail & Related papers  (2024-07-18T00:58:41Z)
• Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning [55.265138447400744]
  Statement-Tuning is a technique that models discriminative tasks as a set of finite statements and trains an encoder model to discriminate between the potential statements to determine the label. Experimental results demonstrate that Statement-Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. The study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement-Tuning can achieve strong performance with modest training data.
  arXiv  Detail & Related papers  (2024-04-19T14:05:03Z)
• Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization [66.08074487429477]
  We investigate the stability and reliability of large language models (LLMs) as automatic evaluators for abstractive summarization. We find that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements.
  arXiv  Detail & Related papers  (2023-05-22T14:58:13Z)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)

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.