·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
GradientStabilizer:Fix the Norm, Not the Gradient2h◆Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning2h◆MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics2h◆Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility2h◆Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift2h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks2h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications2h◆HEAL: Resilient and Self-* Hub-based Learning2h◆ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention2h◆Fitting Unknown Number of Hyperplanes with Manifold Optimization2h◆Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation2h◆Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory2h◆SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints2h◆Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective2h◆Resource-Constrained Affect Modelling via Variance Regularisation Pruning2h◆BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving2h◆Energy-Structured Low-Rank Adaptation for Continual Learning2h◆Conformal Prediction for Hierarchical Data2h◆HARP: Measuring Harm Amplification in Multi-Agent LLM Systems2h◆Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?2h◆GradientStabilizer:Fix the Norm, Not the Gradient2h◆Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning2h◆MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics2h◆Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility2h◆Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift2h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks2h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications2h◆HEAL: Resilient and Self-* Hub-based Learning2h◆ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention2h◆Fitting Unknown Number of Hyperplanes with Manifold Optimization2h◆Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation2h◆Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory2h◆SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints2h◆Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective2h◆Resource-Constrained Affect Modelling via Variance Regularisation Pruning2h◆BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving2h◆Energy-Structured Low-Rank Adaptation for Continual Learning2h◆Conformal Prediction for Hierarchical Data2h◆HARP: Measuring Harm Amplification in Multi-Agent LLM Systems2h◆Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?2h◆
News/Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization
arxiv
PublishedMay 28, 2026 at 4:00 AM

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization

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

arXiv:2605.28802v1 Announce Type: new Abstract: Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisions. We study whether large language models (LLMs) can learn and reproduce such annotator-specific l

Stay posted· Newsletter

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

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

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivGradientStabilizer:Fix the Norm, Not the Gradient2harxivProbability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning2harxivMathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics2harxivComparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility2h
The Bubble Brief
WEEKLY

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

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

Originally published on arxiv ↗
HomeModelsNews