·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models2h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders2h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA2h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging2h◆Multi-Mask Diffusion Language Models for Few-Step Generation2h◆Solar Open 2 Technical Report2h◆The Geometry of Personality: Activation Steering with Jungian Cognitive Functions2h◆Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning2h◆H$^2$SD: Hybrid Hindsight Self-Distillation2h◆LunarFM: A Shared Multimodal Representation of the Moon's Surface2h◆Prior laundering: learned priors with inherited, undetectable overconfidence2h◆Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery2h◆Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting2h◆CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference2h◆Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support2h◆Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs2h◆Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models2h◆A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data2h◆Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics2h◆Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO2h◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models2h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders2h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA2h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging2h◆Multi-Mask Diffusion Language Models for Few-Step Generation2h◆Solar Open 2 Technical Report2h◆The Geometry of Personality: Activation Steering with Jungian Cognitive Functions2h◆Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning2h◆H$^2$SD: Hybrid Hindsight Self-Distillation2h◆LunarFM: A Shared Multimodal Representation of the Moon's Surface2h◆Prior laundering: learned priors with inherited, undetectable overconfidence2h◆Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery2h◆Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting2h◆CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference2h◆Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support2h◆Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs2h◆Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models2h◆A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data2h◆Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics2h◆Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO2h◆
News/LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline
arxiv
PublishedJune 17, 2026 at 4:00 AM
▲bullish

LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2606.17507v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines t

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
01
  • 01
    LLM
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#education#assessment#language-models#software-engineering

No replies yet. Be first.

Mentioned models
01
  • 01
    LLM
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#education#assessment#language-models#software-engineering

Related coverage

More from ARXIV
arxivA Consensus-Based Framework for Relative Preference Evaluation of Large Language Models2harxivProbing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders2harxivData Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA2harxivEnjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging2h
The Bubble Brief
WEEKLY

Read education insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews