Buchumschlag

Controlling Cloze-test Question Item Difficulty with PLM-based Surrogate Models for IRT Assessment

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Jingshen, Xie, Jiajun, Qiu, Xinying
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence Computers and Society
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

The Impact of Item-Writing Flaws on Difficulty and Discrimination in Item Response Theory
von: Schmucker, Robin, et al.
Veröffentlicht: (2025)

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
von: Li, Ming, et al.
Veröffentlicht: (2025)

Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs
von: Wachter, Jasmin, et al.
Veröffentlicht: (2025)

DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation
von: Huang, Tianyou, et al.
Veröffentlicht: (2025)

Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling
von: Liu, Yuanhao, et al.
Veröffentlicht: (2026)

Difficulty-Controllable Cloze Question Distractor Generation
von: Kang, Seokhoon, et al.
Veröffentlicht: (2025)

Constructing Cloze Questions Generatively
von: Sun, Yicheng, et al.
Veröffentlicht: (2024)

Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis
von: Liu, Yunting, et al.
Veröffentlicht: (2024)

Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias
von: Wu, Sirui, et al.
Veröffentlicht: (2025)

Label Confidence Weighted Learning for Target-level Sentence Simplification
von: Qiu, Xinying, et al.
Veröffentlicht: (2024)

NLP Cluster Analysis of Common Core State Standards and NAEP Item Specifications
von: Camilli, Gregory, et al.
Veröffentlicht: (2024)

JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory
von: Yao, Louie Hong, et al.
Veröffentlicht: (2025)

Augmenting Rating-Scale Measures with Text-Derived Items Using the Information-Determined Scoring (IDS) Framework
von: Watson, Joe, et al.
Veröffentlicht: (2025)

Towards Enriched Controllability for Educational Question Generation
von: Leite, Bernardo, et al.
Veröffentlicht: (2023)

Length-Induced Embedding Collapse in PLM-based Models
von: Zhou, Yuqi, et al.
Veröffentlicht: (2024)

Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models
von: Chen, Yuyan, et al.
Veröffentlicht: (2024)

Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench
von: Wang, Tianyu, et al.
Veröffentlicht: (2026)

QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation
von: Nguyen, Bang, et al.
Veröffentlicht: (2025)

Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge
von: Usmanova, Aida, et al.
Veröffentlicht: (2024)

SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction
von: Scarlatos, Alexander, et al.
Veröffentlicht: (2025)

On the Credibility of Evaluating LLMs using Survey Questions
von: Libovický, Jindřich
Veröffentlicht: (2026)

Social Bias in Popular Question-Answering Benchmarks
von: Kraft, Angelie, et al.
Veröffentlicht: (2025)

Understanding Social Support Needs in Questions: A Hybrid Approach Integrating Semi-Supervised Learning and LLM-based Data Augmentation
von: Kuang, Junwei, et al.
Veröffentlicht: (2025)

EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation
von: Jia, Rui, et al.
Veröffentlicht: (2025)

DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
von: Bae, Suyoung, et al.
Veröffentlicht: (2025)

Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek
von: Qiu, Peiran, et al.
Veröffentlicht: (2025)

Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions
von: Atif, Farah, et al.
Veröffentlicht: (2025)

Psychological Assessments with Large Language Models: A Privacy-Focused and Cost-Effective Approach
von: Blanco-Cuaresma, Sergi
Veröffentlicht: (2024)

Evaluating Psychological Safety of Large Language Models
von: Li, Xingxuan, et al.
Veröffentlicht: (2022)

Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
von: Sun, Yuxi, et al.
Veröffentlicht: (2025)

On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral
von: Steenhuis, Quinten, et al.
Veröffentlicht: (2026)

It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education
von: Singh, Shrutika, et al.
Veröffentlicht: (2025)

UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice Questions
von: Rogoz, Ana-Cristina, et al.
Veröffentlicht: (2024)

Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries
von: Wu, Jiageng, et al.
Veröffentlicht: (2023)

Synthetic Student Responses: LLM-Extracted Features for IRT Difficulty Parameter Estimation
von: Hoyl, Matias
Veröffentlicht: (2026)

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
von: Duan, Shitong, et al.
Veröffentlicht: (2023)

When AI Meets Early Childhood Education: Large Language Models as Assessment Teammates in Chinese Preschools
von: Li, Xingming, et al.
Veröffentlicht: (2026)

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
von: Xu, Rongwu, et al.
Veröffentlicht: (2024)

Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
von: Haider, Batool, et al.
Veröffentlicht: (2025)

Implicit assessment of language learning during practice as accurate as explicit testing
von: Hou, Jue, et al.
Veröffentlicht: (2024)